AI For Business Analysts

AI For Business Analysts — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Visual servoing

Visual servoing, also known as vision-based robot control and abbreviated VS, is a technique which uses feedback information extracted from a vision sensor (visual feedback) to control the motion of a robot. One of the earliest papers that talks about visual servoing was from the SRI International Labs in 1979. == Visual servoing taxonomy == There are two fundamental configurations of the robot end-effector (hand) and the camera: Eye-in-hand, or end-point open-loop control, where the camera is attached to the moving hand and observing the relative position of the target. Eye-to-hand, or end-point closed-loop control, where the camera is fixed in the world and observing the target and the motion of the hand. Visual Servoing control techniques are broadly classified into the following types: Image-based (IBVS) Position/pose-based (PBVS) Hybrid approach IBVS was proposed by Weiss and Sanderson. The control law is based on the error between current and desired features on the image plane, and does not involve any estimate of the pose of the target. The features may be the coordinates of visual features, lines or moments of regions. IBVS has difficulties with motions very large rotations, which has come to be called camera retreat. PBVS is a model-based technique (with a single camera). This is because the pose of the object of interest is estimated with respect to the camera and then a command is issued to the robot controller, which in turn controls the robot. In this case the image features are extracted as well, but are additionally used to estimate 3D information (pose of the object in Cartesian space), hence it is servoing in 3D. Hybrid approaches use some combination of the 2D and 3D servoing. There have been a few different approaches to hybrid servoing 2-1/2-D Servoing Motion partition-based Partitioned DOF Based == Survey == The following description of the prior work is divided into 3 parts Survey of existing visual servoing methods. Various features used and their impacts on visual servoing. Error and stability analysis of visual servoing schemes. === Survey of existing visual servoing methods === Visual servo systems, also called servoing, have been around since the early 1980s , although the term visual servo itself was only coined in 1987. Visual Servoing is, in essence, a method for robot control where the sensor used is a camera (visual sensor). Servoing consists primarily of two techniques, one involves using information from the image to directly control the degrees of freedom (DOF) of the robot, thus referred to as Image Based Visual Servoing (IBVS). While the other involves the geometric interpretation of the information extracted from the camera, such as estimating the pose of the target and parameters of the camera (assuming some basic model of the target is known). Other servoing classifications exist based on the variations in each component of a servoing system , e.g. the location of the camera, the two kinds are eye-in-hand and hand–eye configurations. Based on the control loop, the two kinds are end-point-open-loop and end-point-closed-loop. Based on whether the control is applied to the joints (or DOF) directly or as a position command to a robot controller the two types are direct servoing and dynamic look-and-move. Being one of the earliest works the authors proposed a hierarchical visual servo scheme applied to image-based servoing. The technique relies on the assumption that a good set of features can be extracted from the object of interest (e.g. edges, corners and centroids) and used as a partial model along with global models of the scene and robot. The control strategy is applied to a simulation of a two and three DOF robot arm. Feddema et al. introduced the idea of generating task trajectory with respect to the feature velocity. This is to ensure that the sensors are not rendered ineffective (stopping the feedback) for any the robot motions. The authors assume that the objects are known a priori (e.g. CAD model) and all the features can be extracted from the object. The work by Espiau et al. discusses some of the basic questions in visual servoing. The discussions concentrate on modeling of the interaction matrix, camera, visual features (points, lines, etc..). In an adaptive servoing system was proposed with a look-and-move servoing architecture. The method used optical flow along with SSD to provide a confidence metric and a stochastic controller with Kalman filtering for the control scheme. The system assumes (in the examples) that the plane of the camera and the plane of the features are parallel., discusses an approach of velocity control using the Jacobian relationship s˙ = Jv˙ . In addition the author uses Kalman filtering, assuming that the extracted position of the target have inherent errors (sensor errors). A model of the target velocity is developed and used as a feed-forward input in the control loop. Also, mentions the importance of looking into kinematic discrepancy, dynamic effects, repeatability, settling time oscillations and lag in response. Corke poses a set of very critical questions on visual servoing and tries to elaborate on their implications. The paper primarily focuses the dynamics of visual servoing. The author tries to address problems like lag and stability, while also talking about feed-forward paths in the control loop. The paper also, tries to seek justification for trajectory generation, methodology of axis control and development of performance metrics. Chaumette in provides good insight into the two major problems with IBVS. One, servoing to a local minima and second, reaching a Jacobian singularity. The author show that image points alone do not make good features due to the occurrence of singularities. The paper continues, by discussing the possible additional checks to prevent singularities namely, condition numbers of J_s and Jˆ+_s, to check the null space of ˆ J_s and J^T_s . One main point that the author highlights is the relation between local minima and unrealizable image feature motions. Over the years many hybrid techniques have been developed. These involve computing partial/complete pose from Epipolar Geometry using multiple views or multiple cameras. The values are obtained by direct estimation or through a learning or a statistical scheme. While others have used a switching approach that changes between image-based and position-based on a Lyapnov function. The early hybrid techniques that used a combination of image-based and pose-based (2D and 3D information) approaches for servoing required either a full or partial model of the object in order to extract the pose information and used a variety of techniques to extract the motion information from the image. used an affine motion model from the image motion in addition to a rough polyhedral CAD model to extract the object pose with respect to the camera to be able to servo onto the object (on the lines of PBVS). 2-1/2-D visual servoing developed by Malis et al. is a well known technique that breaks down the information required for servoing into an organized fashion which decouples rotations and translations. The papers assume that the desired pose is known a priori. The rotational information is obtained from partial pose estimation, a homography, (essentially 3D information) giving an axis of rotation and the angle (by computing the eigenvalues and eigenvectors of the homography). The translational information is obtained from the image directly by tracking a set of feature points. The only conditions being that the feature points being tracked never leave the field of view and that a depth estimate be predetermined by some off-line technique. 2-1/2-D servoing has been shown to be more stable than the techniques that preceded it. Another interesting observation with this formulation is that the authors claim that the visual Jacobian will have no singularities during the motions. The hybrid technique developed by Corke and Hutchinson, popularly called portioned approach partitions the visual (or image) Jacobian into motions (both rotations and translations) relating X and Y axes and motions related to the Z axis. outlines the technique, to break out columns of the visual Jacobian that correspond to the Z axis translation and rotation (namely, the third and sixth columns). The partitioned approach is shown to handle the Chaumette Conundrum discussed in. This technique requires a good depth estimate in order to function properly. outlines a hybrid approach where the servoing task is split into two, namely main and secondary. The main task is keep the features of interest within the field of view. While the secondary task is to mark a fixation point and use it as a reference to bring the camera to the desired pose. The technique does need a depth estimate from an off-line procedure. The paper discusses two examples for which depth estimates are obtained from robot odometry and by assuming that all
Read more →
Outline of natural language processing

Natural language processing is computer activity in which computers are entailed to analyze, understand, alter, or generate natural language. This includes the automation of any or all linguistic forms, activities, or methods of communication, such as conversation, correspondence, reading, written composition, dictation, publishing, translation, lip reading, and so on. Natural-language processing is also the name of the branch of computer science, artificial intelligence, and linguistics concerned with enabling computers to engage in communication using natural language(s) in all forms, including but not limited to speech, print, writing, and signing. The following outline is provided as an overview of and topical guide to natural-language processing: == Natural-language processing == Natural-language processing can be described as all of the following: A field of science – systematic enterprise that builds and organizes knowledge in the form of testable explanations and predictions about the universe. An applied science – field that applies human knowledge to build or design useful things. A field of computer science – scientific and practical approach to computation and its applications. A branch of artificial intelligence – intelligence of machines and robots and the branch of computer science that aims to create it. A subfield of computational linguistics – interdisciplinary field dealing with the statistical or rule-based modeling of natural language from a computational perspective. An application of engineering – science, skill, and profession of acquiring and applying scientific, economic, social, and practical knowledge, in order to design and also build structures, machines, devices, systems, materials and processes. An application of software engineering – application of a systematic, disciplined, quantifiable approach to the design, development, operation, and maintenance of software, and the study of these approaches; that is, the application of engineering to software. A subfield of computer programming – process of designing, writing, testing, debugging, and maintaining the source code of computer programs. This source code is written in one or more programming languages (such as Java, C++, C#, Python, etc.). The purpose of programming is to create a set of instructions that computers use to perform specific operations or to exhibit desired behaviors. A subfield of artificial intelligence programming – A type of system – set of interacting or interdependent components forming an integrated whole or a set of elements (often called 'components' ) and relationships which are different from relationships of the set or its elements to other elements or sets. A system that includes software – software is a collection of computer programs and related data that provides the instructions for telling a computer what to do and how to do it. Software refers to one or more computer programs and data held in the storage of the computer. In other words, software is a set of programs, procedures, algorithms and its documentation concerned with the operation of a data processing system. A type of technology – making, modification, usage, and knowledge of tools, machines, techniques, crafts, systems, methods of organization, in order to solve a problem, improve a preexisting solution to a problem, achieve a goal, handle an applied input/output relation or perform a specific function. It can also refer to the collection of such tools, machinery, modifications, arrangements and procedures. Technologies significantly affect human as well as other animal species' ability to control and adapt to their natural environments. A form of computer technology – computers and their application. NLP makes use of computers, image scanners, microphones, and many types of software programs. Language technology – consists of natural-language processing (NLP) and computational linguistics (CL) on the one hand, and speech technology on the other. It also includes many application oriented aspects of these. It is often called human language technology (HLT). == Prerequisite technologies == The following technologies make natural-language processing possible: Communication – the activity of a source sending a message to a receiver Language – Speech – Writing – Computing – Computers – Computer programming – Information extraction – User interface – Software – Text editing – program used to edit plain text files Word processing – piece of software used for composing, editing, formatting, printing documents Input devices – pieces of hardware for sending data to a computer to be processed Computer keyboard – typewriter style input device whose input is converted into various data depending on the circumstances Image scanners – == Subfields of natural-language processing == Information extraction (IE) – field concerned in general with the extraction of semantic information from text. This covers tasks such as named-entity recognition, coreference resolution, relationship extraction, etc. Ontology engineering – field that studies the methods and methodologies for building ontologies, which are formal representations of a set of concepts within a domain and the relationships between those concepts. Speech processing – field that covers speech recognition, text-to-speech and related tasks. Statistical natural-language processing – Statistical semantics – a subfield of computational semantics that establishes semantic relations between words to examine their contexts. Distributional semantics – a subfield of statistical semantics that examines the semantic relationship of words across a corpora or in large samples of data. == Related fields == Natural-language processing contributes to, and makes use of (the theories, tools, and methodologies from), the following fields: Automated reasoning – area of computer science and mathematical logic dedicated to understanding various aspects of reasoning, and producing software which allows computers to reason completely, or nearly completely, automatically. A sub-field of artificial intelligence, automatic reasoning is also grounded in theoretical computer science and philosophy of mind. Linguistics – scientific study of human language. Natural-language processing requires understanding of the structure and application of language, and therefore it draws heavily from linguistics. Applied linguistics – interdisciplinary field of study that identifies, investigates, and offers solutions to language-related real-life problems. Some of the academic fields related to applied linguistics are education, linguistics, psychology, computer science, anthropology, and sociology. Some of the subfields of applied linguistics relevant to natural-language processing are: Bilingualism / Multilingualism – Computer-mediated communication (CMC) – any communicative transaction that occurs through the use of two or more networked computers. Research on CMC focuses largely on the social effects of different computer-supported communication technologies. Many recent studies involve Internet-based social networking supported by social software. Contrastive linguistics – practice-oriented linguistic approach that seeks to describe the differences and similarities between a pair of languages. Conversation analysis (CA) – approach to the study of social interaction, embracing both verbal and non-verbal conduct, in situations of everyday life. Turn-taking is one aspect of language use that is studied by CA. Discourse analysis – various approaches to analyzing written, vocal, or sign language use or any significant semiotic event. Forensic linguistics – application of linguistic knowledge, methods and insights to the forensic context of law, language, crime investigation, trial, and judicial procedure. Interlinguistics – study of improving communications between people of different first languages with the use of ethnic and auxiliary languages (lingua franca). For instance by use of intentional international auxiliary languages, such as Esperanto or Interlingua, or spontaneous interlanguages known as pidgin languages. Language assessment – assessment of first, second or other language in the school, college, or university context; assessment of language use in the workplace; and assessment of language in the immigration, citizenship, and asylum contexts. The assessment may include analyses of listening, speaking, reading, writing or cultural understanding, with respect to understanding how the language works theoretically and the ability to use the language practically. Language pedagogy – science and art of language education, including approaches and methods of language teaching and study. Natural-language processing is used in programs designed to teach language, including first- and second-language training. Language planning – Language policy – Lexicography – Literacies – Pragmatics – Second-language acquisition – Stylistics – Translation – Comp
Read more →
Mark V. Shaney

Mark V. Shaney is a synthetic Usenet user whose postings in the net.singles newsgroups were generated by Markov chain techniques, based on text from other postings. The username is a play on the words "Markov chain". Many readers were fooled into thinking that the quirky, sometimes uncannily topical posts were written by a real person. The system was designed by Rob Pike with coding by Bruce Ellis. Don P. Mitchell wrote the Markov chain code, initially demonstrating it to Pike and Ellis using the Tao Te Ching as a basis. They chose to apply it to the net.singles netnews group. The program is fairly simple. It ingests the sample text (the Tao Te Ching, or the posts of a Usenet group) and creates a massive list of every sequence of three successive words (triplet) which occurs in the text. It then chooses two words at random, and looks for a word which follows those two in one of the triplets in its massive list. If there is more than one, it picks at random (identical triplets count separately, so a sequence which occurs twice is twice as likely to be picked as one which only occurs once). It then adds that word to the generated text. Then, in the same way, it picks a triplet that starts with the second and third words in the generated text, and that gives a fourth word. It adds the fourth word, then repeats with the third and fourth words, and so on. This algorithm is called a third-order Markov chain (because it uses sequences of three words). == Examples == A classic example, from 1984, originally sent as a mail message, later posted to net.singles is reproduced here: >From mvs Fri Nov 16 17:11 EST 1984 remote from alice It looks like Reagan is going to say? Ummm... Oh yes, I was looking for. I'm so glad I remembered it. Yeah, what I have wondered if I had committed a crime. Don't eat with your assessment of Reagon and Mondale. Up your nose with a guy from a firm that specifically researches the teen-age market. As a friend of mine would say, "It really doesn't matter"... It looks like Reagan is holding back the arms of the American eating public have changed dramatically, and it got pretty boring after about 300 games. People, having a much larger number of varieties, and are very different from what one can find in Chinatowns across the country (things like pork buns, steamed dumplings, etc.) They can be cheap, being sold for around 30 to 75 cents apiece (depending on size), are generally not greasy, can be adequately explained by stupidity. Singles have felt insecure since we came down from the Conservative world at large. But Chuqui is the way it happened and the prices are VERY reasonable. Can anyone think of myself as a third sex. Yes, I am expected to have. People often get used to me knowing these things and then a cover is placed over all of them. Along the side of the $$ are spent by (or at least for ) the girls. You can't settle the issue. It seems I've forgotten what it is, but I don't. I know about violence against women, and I really doubt they will ever join together into a large number of jokes. It showed Adam, just after being created. He has a modem and an autodial routine. He calls my number 1440 times a day. So I will conclude by saying that I can well understand that she might soon have the time, it makes sense, again, to get the gist of my argument, I was in that (though it's a Republican administration). _-_-_-_-Mark Other quotations from Mark's Usenet posts are: "I spent an interesting evening recently with a grain of salt." (Alternatively reported as "While at a conference a few weeks back, I spent an interesting evening with a grain of salt.") "I hope that there are sour apples in every bushel." (see also sour grapes) == History == In The Usenet Handbook Mark Harrison writes that after September 1981, students joined Usenet en masse, "creating the USENET we know today: endless dumb questions, endless idiots posing as savants, and (of course) endless victims for practical jokes." In December, Rob Pike created the netnews group net.suicide as prank, "a forum for bad jokes". Some users thought it was a legitimate forum, some discussed "riding motorcycles without helmets". At first, most posters were "real people", but soon "characters" began posting. Pike created a "vicious" character named Bimmler. At its peak, net.suicide had ten frequent posters; nine were "known to be characters." But ultimately, Pike deleted the newsgroup because it was too much work to maintain; Bimmler messages were created "by hand". The "obvious alternative" was software, running on a Bell Labs computer created by Bruce Ellis, based on the Markov code by Don Mitchell, which became the online character Mark V. Shaney. Kernighan and Pike listed Mark V. Shaney in the acknowledgements in The Practice of Programming, noting its roots in Mitchell's markov, which, adapted as shaney, was used for "humorous deconstructionist activities" in the 1980s. Dewdney pointed out "perhaps Mark V. Shaney's magnum opus: a 20-page commentary on the deconstructionist philosophy of Jean Baudrillard" directed by Pike, with assistance from Henry S. Baird and Catherine Richards, to be distributed by email. The piece was based on Jean Baudrillard's "The Precession of Simulacra", published in Simulacra and Simulation (1981). == Reception == The program was discussed by A. K. Dewdney in the Scientific American "Computer Recreations" column in 1989, by Penn Jillette in his PC Computing column in 1991, and in several books, including the Usenet Handbook, Bots: the Origin of New Species, Hippo Eats Dwarf: A Field Guide to Hoaxes and Other B.S., and non-computer-related journals such as Texas Studies in Literature and Language. Dewdney wrote about the program's output, "The overall impression is not unlike what remains in the brain of an inattentive student after a late-night study session. Indeed, after reading the output of Mark V. Shaney, I find ordinary writing almost equally strange and incomprehensible!" He noted the reactions of newsgroup users, who have "shuddered at Mark V. Shaney's reflections, some with rage and others with laughter:" The opinions of the new net.singles correspondent drew mixed reviews. Serious users of the bulletin board's services sensed satire. Outraged, they urged that someone "pull the plug" on Mark V. Shaney's monstrous rantings. Others inquired almost admiringly whether the program was a secret artificial intelligence project that was being tested in a human conversational environment. A few may even have thought that Mark V. Shaney was a real person, a tortured schizophrenic desperately seeking a like-minded companion. Concluding, Dewdney wrote, "If the purpose of computer prose is to fool people into thinking that it was written by a sane person, Mark V. Shaney probably falls short." A 2012 article in Observer compared Mark V. Shaney's "strangely beautiful" postings to the Horse_ebooks account on Twitter and music reviews at Pitchfork, saying that "this mash-up of gibberish and human sentiment" is what "made Mark V. Shaney so endlessly fascinating".
Read more →
Neural operators

Neural operators are a class of deep learning architectures designed to learn maps between infinite-dimensional function spaces. Neural operators represent an extension of traditional artificial neural networks, marking a departure from the typical focus on learning mappings between finite-dimensional Euclidean spaces or finite sets. Neural operators directly learn operators between function spaces; they can receive input functions, and the output function can be evaluated at any discretization. The primary application of neural operators is in learning surrogate maps for the solution operators of partial differential equations (PDEs), which are critical tools in modeling the natural environment. Standard PDE solvers can be time-consuming and computationally intensive, especially for complex systems. Neural operators have demonstrated improved performance in solving PDEs compared to existing machine learning methodologies while being significantly faster than numerical solvers. Neural operators have also been applied to various scientific and engineering disciplines such as turbulent flow modeling, computational mechanics, graph-structured data, and the geosciences. In particular, they have been applied to learning stress-strain fields in materials, classifying complex data like spatial transcriptomics, predicting multiphase flow in porous media, and carbon dioxide migration simulations. Finally, the operator learning paradigm allows learning maps between function spaces, and is different from parallel ideas of learning maps from finite-dimensional spaces to function spaces, and subsumes these settings as special cases when limited to a fixed input resolution. == Operator learning == Understanding and mapping relationships between function spaces has many applications in engineering and the sciences. In particular, one can cast the problem of solving partial differential equations as identifying a map between function spaces, such as from an initial condition to a time-evolved state. In other PDEs this map takes an input coefficient function and outputs a solution function. Operator learning is a machine learning paradigm to learn solution operators mapping the input function to the output function . Using traditional machine learning methods, addressing this problem would involve discretizing the infinite-dimensional input and output function spaces into finite-dimensional grids and applying standard learning models, such as neural networks. This approach reduces the operator learning to finite-dimensional function learning and has some limitations, such as generalizing to discretizations beyond the grid used in training. The primary properties of neural operators that differentiate them from traditional neural networks is discretization invariance and discretization convergence. Unlike conventional neural networks, which are fixed on the discretization of training data, neural operators can adapt to various discretizations without re-training. This property improves the robustness and applicability of neural operators in different scenarios, providing consistent performance across different resolutions and grids. == Definition and formulation == Architecturally, neural operators are similar to feed-forward neural networks in the sense that they are composed of alternating linear maps and non-linearities. Since neural operators act on and output functions, neural operators have been instead formulated as a sequence of alternating linear integral operators on function spaces and point-wise non-linearities. Using an analogous architecture to finite-dimensional neural networks, similar universal approximation theorems have been proven for neural operators. In particular, it has been shown that neural operators can approximate any continuous operator on a compact set. Neural operators seek to approximate some operator G : A → U {\displaystyle {\mathcal {G}}:{\mathcal {A}}\to {\mathcal {U}}} between function spaces A {\displaystyle {\mathcal {A}}} and U {\displaystyle {\mathcal {U}}} by building a parametric map G ϕ : A → U {\displaystyle {\mathcal {G}}_{\phi }:{\mathcal {A}}\to {\mathcal {U}}} . Such parametric maps G ϕ {\displaystyle {\mathcal {G}}_{\phi }} can generally be defined in the form G ϕ := Q ∘ σ ( W T + K T + b T ) ∘ ⋯ ∘ σ ( W 1 + K 1 + b 1 ) ∘ P , {\displaystyle {\mathcal {G}}_{\phi }:={\mathcal {Q}}\circ \sigma (W_{T}+{\mathcal {K}}_{T}+b_{T})\circ \cdots \circ \sigma (W_{1}+{\mathcal {K}}_{1}+b_{1})\circ {\mathcal {P}},} where P , Q {\displaystyle {\mathcal {P}},{\mathcal {Q}}} are the lifting (lifting the codomain of the input function to a higher dimensional space) and projection (projecting the codomain of the intermediate function to the output dimension) operators, respectively. These operators act pointwise on functions and are typically parametrized as multilayer perceptrons. σ {\displaystyle \sigma } is a pointwise nonlinearity, such as a rectified linear unit (ReLU), or a Gaussian error linear unit (GeLU). Each layer t = 1 , … , T {\displaystyle t=1,\dots ,T} has a respective local operator W t {\displaystyle W_{t}} (usually parameterized by a pointwise neural network), a kernel integral operator K t {\displaystyle {\mathcal {K}}_{t}} , and a bias function b t {\displaystyle b_{t}} . Given some intermediate functional representation v t {\displaystyle v_{t}} with domain D {\displaystyle D} in the t {\displaystyle t} -th hidden layer, a kernel integral operator K ϕ {\displaystyle {\mathcal {K}}_{\phi }} is defined as ( K ϕ v t ) ( x ) := ∫ D κ ϕ ( x , y , v t ( x ) , v t ( y ) ) v t ( y ) d y , {\displaystyle ({\mathcal {K}}_{\phi }v_{t})(x):=\int _{D}\kappa _{\phi }(x,y,v_{t}(x),v_{t}(y))v_{t}(y)dy,} where the kernel κ ϕ {\displaystyle \kappa _{\phi }} is a learnable implicit neural network, parametrized by ϕ {\displaystyle \phi } . In practice, one is often given the input function to the neural operator at a specific resolution. For instance, consider the setting where one is given the evaluation of v t {\displaystyle v_{t}} at n {\displaystyle n} points { y j } j n {\displaystyle \{y_{j}\}_{j}^{n}} . Borrowing from Nyström integral approximation methods such as Riemann sum integration and Gaussian quadrature, the above integral operation can be computed as follows: ∫ D κ ϕ ( x , y , v t ( x ) , v t ( y ) ) v t ( y ) d y ≈ ∑ j n κ ϕ ( x , y j , v t ( x ) , v t ( y j ) ) v t ( y j ) Δ y j , {\displaystyle \int _{D}\kappa _{\phi }(x,y,v_{t}(x),v_{t}(y))v_{t}(y)dy\approx \sum _{j}^{n}\kappa _{\phi }(x,y_{j},v_{t}(x),v_{t}(y_{j}))v_{t}(y_{j})\Delta _{y_{j}},} where Δ y j {\displaystyle \Delta _{y_{j}}} is the sub-area volume or quadrature weight associated to the point y j {\displaystyle y_{j}} . Thus, a simplified layer can be computed as v t + 1 ( x ) ≈ σ ( ∑ j n κ ϕ ( x , y j , v t ( x ) , v t ( y j ) ) v t ( y j ) Δ y j + W t ( v t ( y j ) ) + b t ( x ) ) . {\displaystyle v_{t+1}(x)\approx \sigma \left(\sum _{j}^{n}\kappa _{\phi }(x,y_{j},v_{t}(x),v_{t}(y_{j}))v_{t}(y_{j})\Delta _{y_{j}}+W_{t}(v_{t}(y_{j}))+b_{t}(x)\right).} The above approximation, along with parametrizing κ ϕ {\displaystyle \kappa _{\phi }} as an implicit neural network, results in the graph neural operator (GNO). There have been various parameterizations of neural operators for different applications. These typically differ in their parameterization of κ {\displaystyle \kappa } . The most popular instantiation is the Fourier neural operator (FNO). FNO takes κ ϕ ( x , y , v t ( x ) , v t ( y ) ) := κ ϕ ( x − y ) {\displaystyle \kappa _{\phi }(x,y,v_{t}(x),v_{t}(y)):=\kappa _{\phi }(x-y)} and by applying the convolution theorem, arrives at the following parameterization of the kernel integral operator: ( K ϕ v t ) ( x ) = F − 1 ( R ϕ ⋅ ( F v t ) ) ( x ) , {\displaystyle ({\mathcal {K}}_{\phi }v_{t})(x)={\mathcal {F}}^{-1}(R_{\phi }\cdot ({\mathcal {F}}v_{t}))(x),} where F {\displaystyle {\mathcal {F}}} represents the Fourier transform and R ϕ {\displaystyle R_{\phi }} represents the Fourier transform of some periodic function κ ϕ {\displaystyle \kappa _{\phi }} . That is, FNO parameterizes the kernel integration directly in Fourier space, using a prescribed number of Fourier modes. When the grid at which the input function is presented is uniform, the Fourier transform can be approximated using the discrete Fourier transform (DFT) with frequencies below some specified threshold. The discrete Fourier transform can be computed using a fast Fourier transform (FFT) implementation. == Training == Training neural operators is similar to the training process for a traditional neural network. Neural operators are typically trained in some Lp norm or Sobolev norm. In particular, for a dataset { ( a i , u i ) } i = 1 N {\displaystyle \{(a_{i},u_{i})\}_{i=1}^{N}} of size N {\displaystyle N} , neural operators minimize (a discretization of) L U ( { ( a i , u i ) } i = 1 N ) := ∑ i = 1 N ‖ u i − G θ ( a i ) ‖ U 2 {\displaystyle {\mathcal {L}}_{\mathca
Read more →
List of monochrome and RGB color formats

This list of monochrome and RGB palettes includes generic repertoires of colors (color palettes) to produce black-and-white and RGB color pictures by a computer's display hardware. RGB is the most common method to produce colors for displays; so these complete RGB color repertoires have every possible combination of R-G-B triplets within any given maximum number of levels per component. Each palette is represented by a series of color patches. When the number of colors is low, a 1-pixel-size version of the palette appears below it, for easily comparing relative palette sizes. Huge palettes are given directly in one-color-per-pixel color patches. For each unique palette, an image color test chart and sample image (truecolor original follows) rendered with that palette (without dithering) are given. The test chart shows the full 256 levels of the red, green, and blue (RGB) primary colors and cyan, magenta, and yellow complementary colors, along with a full 256-level grayscale. Gradients of RGB intermediate colors (orange, lime green, sea green, sky blue, violet, and fuchsia), and a full hue spectrum are also present. Color charts are not gamma corrected. These elements illustrate the color depth and distribution of the colors of any given palette, and the sample image indicates how the color selection of such palettes could represent real-life images. These images are not necessarily representative of how the image would be displayed on the original graphics hardware, as the hardware may have additional limitations regarding the maximum display resolution, pixel aspect ratio and color placement. Implementation of these formats is specific to each machine. Therefore, the number of colors that can be simultaneously displayed in a given text or graphic mode might be different. Also, the actual displayed colors are subject to the output format used - PAL or NTSC, composite or component video, etc. - and might be slightly different. For simulated images and specific hardware and alternate methods to produce colors other than RGB (ex: composite), see the List of 8-bit computer hardware palettes, the List of 16-bit computer hardware palettes and the List of video game console palettes. For various software arrangements and sorts of colors, including other possible full RGB arrangements within 8-bit color depth displays, see the List of software palettes. == Monochrome palettes == These palettes only have some shades of gray, from black to white (considered the darkest and lightest "grays", respectively). The general rule is that those palettes have 2n different shades of gray, where n is the number of bits needed to represent a single pixel. === Monochrome (1-bit grayscale) === Monochrome graphics displays typically have a black background with a white or light gray image, though green and amber monochrome monitors were also common. Such a palette requires only one bit per pixel. Where photo-realism was desired, these early computer systems had a heavy reliance on dithering to make up for the limits of the technology. In some systems, as Hercules and CGA graphic cards for the IBM PC, a bit value of 1 represents white pixels (light on) and a value of 0 the black ones (light off); others, like the Playdate and Atari ST and Apple Macintosh with monochrome monitors, a bit value of 0 means a white pixel (no ink) and a value of 1 means a black pixel (dot of ink), which it approximates to the printing logic. === 2-bit Grayscale === In a 2-bit color palette each pixel's value is represented by 2 bits resulting in a 4-value palette (22 = 4). 2-bit dithering: It has black, white and two intermediate levels of gray as follows: A monochrome 2-bit palette is used on: The Monochrome Display Adapter for the IBM PC NeXT Computer, NeXTcube and NeXTstation monochrome graphic displays. Original Game Boy system portable video game console. Macintosh PowerBook 150 monochrome LC displays. Amiga with A2024 monochrome monitor in high-resolution mode. The original Amazon Kindle The original WonderSwan The Tiger Electronics Game.com portable video game console The original Neo Geo Pocket. === 4-bit Grayscale === In a 4-bit color palette each pixel's value is represented by 4 bits resulting in a 16-value palette (24 = 16): 4-bit grayscale dithering does a fairly good job of reducing visible banding of the level changes: A monochrome 4-bit palette is used on: MOS Technology VDC (on the Commodore 128 with monochrome monitor) Amstrad CPC series with a GT64/GT65 Green Monitor (16 unique green shades) Amstrad CPC Plus series with the MM12 Monochrome monitor (16 shades of grey) Some Apple PowerBooks equipped with monochrome displays like the PowerBook 5300 The original VideoNow === 8-bit Grayscale === In an 8-bit color palette each pixel's value is represented by 8 bits resulting in a 256-value palette (28 = 256). This is usually the maximum number of grays in ordinary monochrome systems; each image pixel occupies a single memory byte. Most scanners can capture images in 8-bit grayscale, and image file formats like TIFF and JPEG natively support this monochrome palette size. Alpha channels employed for video overlay also use (conceptually) this palette. The gray level indicates the opacity of the blended image pixel over the background image pixel. == Dichrome palettes == === 16-bit RG palette === The RG or red–green color space is a color space that uses only two primary colors: red and green. It was used on early color processes for films. It was used as an additive format, similar to the RGB color model but without a blue channel, on processes such as Kinemacolor, Prizma, Technicolor I, Raycol, etc., producing shades of black, red, green and yellow. Alternatively, it was used as a subtractive format on Brewster Color I, Kodachrome I, Prizma II, Technicolor II, etc., producing shades of transparent, red, green and black. Until recently, its primary use was in low-cost light-emitting diode displays in which red and green tended to be far more common than the still nascent blue LED technology, but full-color LEDs with blue have become more common in recent years. ColorCode 3-D, a anaglyph stereoscopic color scheme, uses the RG color space to simulate a broad spectrum of color in one eye, while the blue portion of the spectrum transmits a black-and-white (black-and-blue) image to the other eye to give depth perception. === 16-bit RB palette === === 16-bit GB palette === == Regular RGB palettes == Here are grouped those full RGB hardware palettes that have the same number of binary levels (i.e., the same number of bits) for every red, green and blue components using the full RGB color model. Thus, the total number of colors are always the number of possible levels by component, n, raised to a power of 3: n×n×n = n3. === 3-bit RGB === 3-bit RGB dithering: Systems with a 3-bit RGB palette use 1 bit for each of the red, green and blue color components. That is, each component is either "on" or "off" with no intermediate states. This results in an 8-color palette ((21)3 = 23 = 8) that has black, white, the three RGB primary colors red, green and blue and their correspondent complementary colors cyan, magenta and yellow as follows: The color indices vary between implementations; therefore, index numbers are not given. The 3-bit RGB palette is used by: Text terminals following the ECMA-48 standard (sometimes known as the "ANSI standard", although ANSI X3.128 does not define colors) World System Teletext Level 1/1.5 Videotex Oric computers BBC Micro PC-8801 (up to the MkII) PC-9801 (with original 8086 CPU, before the VM/VX models) Sharp X1 (models before the X1 Turbo Z) Sharp MZ 700 FM-7, FM New 7, FM 77 (before the FM77AV) Sinclair QL Space Invaders Part II (arcade hardware) Macintosh SE (with a color printer or external monitor) Atari 2600 (SECAM version) Color Maximite (PIC32 based microcomputer) Arcadia 2001 PV-1000 Monkey Magic (arcade hardware) VIC-20 (high-res mode) Mouse Trap (arcade hardware) Sanyo MBC-550 series Windows 1.0 (includes dithering) === 6-bit RGB === Systems with a 6-bit RGB palette use 2 bits for each of the red, green, and blue color components. This results in a (22)3 = 43 = 64-color palette as follows: 6-bit RGB systems include the following: Enhanced Graphics Adapter (EGA) for IBM PC/AT (16 colors at once) Sega Master System video game console (32 colors at once) GIME for TRS-80 Color Computer 3 (16 colors at once) Pebble Time smartwatch which has a 6-bit (64 color) e-paper display Parallax Propeller using the reference VGA circuit === 9-bit RGB === Systems with a 9-bit RGB palette use 3 bits for each of the red, green, and blue color components. This results in a (23)3 = 83 = 512-color palette as follows: 9-bit RGB systems include the following: Atari ST (Normally 4 to 16 at once without tricks) MSX2 computers (up to 16 at once) Sega Genesis video game console, (64 colors at once) Sega Nomad TurboGrafx-16 (NEC PC-Engine) ZX Spectrum Next The NEC PC-88
Read more →
Salience (neuroscience)

Salience (also called saliency, from Latin saliō meaning "leap, spring") is the property by which some thing stands out. Salient events are an attentional mechanism by which organisms learn and survive; those organisms can focus their limited perceptual and cognitive resources on the pertinent (that is, salient) subset of the sensory data available to them. Saliency typically arises from contrasts between items and their neighborhood. They might be represented, for example, by a red dot surrounded by white dots, or by a flickering message indicator of an answering machine, or a loud noise in an otherwise quiet environment. Saliency detection is often studied in the context of the visual system, but similar mechanisms operate in other sensory systems. Just what is salient can be influenced by training: for example, for human subjects particular letters can become salient by training. There can be a sequence of necessary events, each of which has to be salient, in turn, in order for successful training in the sequence; the alternative is a failure, as in an illustrated sequence when tying a bowline; in the list of illustrations, even the first illustration is a salient: the rope in the list must cross over, and not under the bitter end of the rope (which can remain fixed, and not free to move); failure to notice that the first salient has not been satisfied means the knot will fail to hold, even when the remaining salient events have been satisfied. When attention deployment is driven by salient stimuli, it is considered to be bottom-up, memory-free, and reactive. Conversely, attention can also be guided by top-down, memory-dependent, or anticipatory mechanisms, such as when looking ahead of moving objects or sideways before crossing streets. Humans and other animals have difficulty paying attention to more than one item simultaneously, so they are faced with the challenge of continuously integrating and prioritizing different bottom-up and top-down influences. == Neuroanatomy == The brain component named the hippocampus helps with the assessment of salience and context by using past memories to filter new incoming stimuli, and placing those that are most important into long term memory. The entorhinal cortex is the pathway into and out of the hippocampus, and is an important part of the brain's memory network; research shows that it is a brain region that suffers damage early on in Alzheimer's disease, one of the effects of which is altered (diminished) salience. The pulvinar nuclei (in the thalamus) modulate physical/perceptual salience in attentional selection. One group of neurons (i.e., D1-type medium spiny neurons) within the nucleus accumbens shell (NAcc shell) assigns appetitive motivational salience ("want" and "desire", which includes a motivational component), aka incentive salience, to rewarding stimuli, while another group of neurons (i.e., D2-type medium spiny neurons) within the NAcc shell assigns aversive motivational salience to aversive stimuli. The primary visual cortex (V1) generates a bottom-up saliency map from visual inputs to guide reflexive attentional shifts or gaze shifts. According to V1 Saliency Hypothesis, the saliency of a location is higher when V1 neurons give higher responses to that location relative to V1 neurons' responses to other visual locations. For example, a unique red item among green items, or a unique vertical bar among horizontal bars, is salient since it evokes higher V1 responses and attracts attention or gaze. The V1 neural responses are sent to the superior colliculus to guide gaze shifts to the salient locations. A fingerprint of the saliency map in V1 is that attention or gaze can be captured by the location of an eye-of-origin singleton in visual inputs, e.g., a bar uniquely shown to the left eye in a background of many other bars shown to the right eye, even when observers cannot tell the difference between the singleton and the background bars. == In psychology == The term is widely used in the study of perception and cognition to refer to any aspect of a stimulus that, for any of many reasons, stands out from the rest. Salience may be the result of emotional, motivational or cognitive factors and is not necessarily associated with physical factors such as intensity, clarity or size. Although salience is thought to determine attentional selection, salience associated with physical factors does not necessarily influence selection of a stimulus. === Salience bias === Salience bias (also referred to as perceptual salience) is a cognitive bias that predisposes individuals to focus on or attend to items, information, or stimuli that are more prominent, visible, or emotionally striking. This is as opposed to stimuli that are unremarkable, or less salient, even though this difference is often irrelevant by objective standards. The American Psychological Association (APA) defines the salience hypothesis as a theory regarding perception where "motivationally significant" information is more readily perceived than information with little or less significant motivational importance. Perceptual salience (salience bias) is linked to the vividness effect, whereby a more pronounced response is produced by a more vivid perception of a stimulus than the mere knowledge of the stimulus. Salience bias assumes that more dynamic, conspicuous, or distinctive stimuli engage attention more than less prominent stimuli, disproportionately impacting decision making, it is a bias which favors more salient information. ==== Application ==== ===== Cognitive Psychology ===== Salience bias, like all other cognitive biases, is an applicable concept to various disciplines. For example, cognitive psychology investigates cognitive functions and processes, such as perception, attention, memory, problem solving, and decision making, all of which could be influenced by salience bias. Salience bias acts to combat cognitive overload by focusing attention on prominent stimuli, which affects how individuals perceive the world as other, less vivid stimuli that could add to or change this perception, are ignored. Human attention gravitates towards novel and relevant stimuli and unconsciously filters out less prominent information, demonstrating salience bias, which influences behavior as human behavior is affected by what is attended to. Behavioral economists Tversky and Kahneman also suggest that the retrieval of instances is influenced by their salience, such as how witnessing or experiencing an event first-hand has a greater impact than when it is less salient, like if it were read about, implying that memory is affected by salience. ===== Language ===== It is also relevant in language understanding and acquisition. Focusing on more salient phenomena allows people to detect language patterns and dialect variations more easily, making dialect categorization more efficient. ===== Social Behavior ===== Furthermore, social behaviors and interactions can also be influenced by perceptual salience. Changes in the perceptual salience of an individual heavily influences their social behavior and subjective experience of their social interactions, confirming a "social salience effect". Social salience relates to how individuals perceive and respond to other people. ===== Behavioral Science ===== The connection between salience bias and other heuristics, like availability and representativeness, links it to the fields of behavioral science and behavioral economics. Salience bias is closely related to the availability heuristic in behavioral economics, based on the influence of information vividness and visibility, such as recency or frequency, on judgements, for example:Accessibility and salience are closely related to availability, and they are important as well. If you have personally experienced a serious earthquake, you're more likely to believe that an earthquake is likely than if you read about it in a weekly magazine. Thus, vivid and easily imagined causes of death (for example, tornadoes) often receive inflated estimates of probability, and less-vivid causes (for example, asthma attacks) receive low estimates, even if they occur with a far greater frequency (here, by a factor of twenty). Timing counts too: more recent events have a greater impact on our behavior, and on our fears, than earlier ones.Humans have bounded rationality, which refers to their limited ability to be rational in decision making, due to a limited capacity to process information and cognitive ability. Heuristics, such as availability, are employed to reduce the complexity of cognitive and social tasks or judgements, in order to decrease the cognitive load that result from bounded rationality. Despite the effectiveness of heuristics in doing so, they are limited by systematic errors that occur, often the result of influencing biases, such as salience. This can lead to misdirected or misinformed judgements, based on an overemphasis or overweighting of
Read more →
Deep learning in photoacoustic imaging

Photoacoustic imaging (PA) is based on the photoacoustic effect, in which optical absorption causes a rise in temperature, which causes a subsequent rise in pressure via thermo-elastic expansion. This pressure rise propagates through the tissue and is sensed via ultrasonic transducers. Due to the proportionality between the optical absorption, the rise in temperature, and the rise in pressure, the ultrasound pressure wave signal can be used to quantify the original optical energy deposition within the tissue. Photoacoustic imaging has applications of deep learning in both photoacoustic computed tomography (PACT) and photoacoustic microscopy (PAM). PACT utilizes wide-field optical excitation and an array of unfocused ultrasound transducers. Similar to other computed tomography methods, the sample is imaged at multiple view angles, which are then used to perform an inverse reconstruction algorithm based on the detection geometry (typically through universal backprojection, modified delay-and-sum, or time reversal ) to elicit the initial pressure distribution within the tissue. PAM on the other hand uses focused ultrasound detection combined with weakly focused optical excitation (acoustic resolution PAM or AR-PAM) or tightly focused optical excitation (optical resolution PAM or OR-PAM). PAM typically captures images point-by-point via a mechanical raster scanning pattern. At each scanned point, the acoustic time-of-flight provides axial resolution while the acoustic focusing yields lateral resolution. == Applications of deep learning in PACT == The first application of deep learning in PACT was by Reiter et al. in which a deep neural network was trained to learn spatial impulse responses and locate photoacoustic point sources. The resulting mean axial and lateral point location errors on 2,412 of their randomly selected test images were 0.28 mm and 0.37 mm respectively. After this initial implementation, the applications of deep learning in PACT have branched out primarily into removing artifacts from acoustic reflections, sparse sampling, limited-view, and limited-bandwidth. There has also been some recent work in PACT toward using deep learning for wavefront localization. There have been networks based on fusion of information from two different reconstructions to improve the reconstruction using deep learning fusion based networks. === Using deep learning to locate photoacoustic point sources === Traditional photoacoustic beamforming techniques modeled photoacoustic wave propagation by using detector array geometry and the time-of-flight to account for differences in the PA signal arrival time. However, this technique failed to account for reverberant acoustic signals caused by acoustic reflection, resulting in acoustic reflection artifacts that corrupt the true photoacoustic point source location information. In Reiter et al., a convolutional neural network (similar to a simple VGG-16 style architecture) was used that took pre-beamformed photoacoustic data as input and outputted a classification result specifying the 2-D point source location. ==== Deep learning for PA wavefront localization ==== Johnstonbaugh et al. was able to localize the source of photoacoustic wavefronts with a deep neural network. The network used was an encoder-decoder style convolutional neural network. The encoder-decoder network was made of residual convolution, upsampling, and high field-of-view convolution modules. A Nyquist convolution layer and differentiable spatial-to-numerical transform layer were also used within the architecture. Simulated PA wavefronts served as the input for training the model. To create the wavefronts, the forward simulation of light propagation was done with the NIRFast toolbox and the light-diffusion approximation, while the forward simulation of sound propagation was done with the K-Wave toolbox. The simulated wavefronts were subjected to different scattering mediums and Gaussian noise. The output for the network was an artifact free heat map of the targets axial and lateral position. The network had a mean error rate of less than 30 microns when localizing target below 40 mm and had a mean error rate of 1.06 mm for localizing targets between 40 mm and 60 mm. With a slight modification to the network, the model was able to accommodate multi target localization. A validation experiment was performed in which pencil lead was submerged into an intralipid solution at a depth of 32 mm. The network was able to localize the lead's position when the solution had a reduced scattering coefficient of 0, 5, 10, and 15 cm−1. The results of the network show improvements over standard delay-and-sum or frequency-domain beamforming algorithms and Johnstonbaugh proposes that this technology could be used for optical wavefront shaping, circulating melanoma cell detection, and real-time vascular surgeries. === Removing acoustic reflection artifacts (in the presence of multiple sources and channel noise) === Building on the work of Reiter et al., Allman et al. utilized a full VGG-16 architecture to locate point sources and remove reflection artifacts within raw photoacoustic channel data (in the presence of multiple sources and channel noise). This utilization of deep learning trained on simulated data produced in the MATLAB k-wave library, and then later reaffirmed their results on experimental data. === Ill-posed PACT reconstruction === In PACT, tomographic reconstruction is performed, in which the projections from multiple solid angles are combined to form an image. When reconstruction methods like filtered backprojection or time reversal, are ill-posed inverse problems due to sampling under the Nyquist-Shannon's sampling requirement or with limited-bandwidth/view, the resulting reconstruction contains image artifacts. Traditionally these artifacts were removed with slow iterative methods like total variation minimization, but the advent of deep learning approaches has opened a new avenue that utilizes a priori knowledge from network training to remove artifacts. In the deep learning methods that seek to remove these sparse sampling, limited-bandwidth, and limited-view artifacts, the typical workflow involves first performing the ill-posed reconstruction technique to transform the pre-beamformed data into a 2-D representation of the initial pressure distribution that contains artifacts. Then, a convolutional neural network (CNN) is trained to remove the artifacts, in order to produce an artifact-free representation of the ground truth initial pressure distribution. ==== Using deep learning to remove sparse sampling artifacts ==== When the density of uniform tomographic view angles is under what is prescribed by the Nyquist-Shannon's sampling theorem, it is said that the imaging system is performing sparse sampling. Sparse sampling typically occurs as a way of keeping production costs low and improving image acquisition speed. The typical network architectures used to remove these sparse sampling artifacts are U-net and Fully Dense (FD) U-net. Both of these architectures contain a compression and decompression phase. The compression phase learns to compress the image to a latent representation that lacks the imaging artifacts and other details. The decompression phase then combines with information passed by the residual connections in order to add back image details without adding in the details associated with the artifacts. FD U-net modifies the original U-net architecture by including dense blocks that allow layers to utilize information learned by previous layers within the dense block. Another technique was proposed using a simple CNN based architecture for removal of artifacts and improving the k-wave image reconstruction. ==== Removing limited-view artifacts with deep learning ==== When a region of partial solid angles are not captured, generally due to geometric limitations, the image acquisition is said to have limited-view. As illustrated by the experiments of Davoudi et al., limited-view corruptions can be directly observed as missing information in the frequency domain of the reconstructed image. Limited-view, similar to sparse sampling, makes the initial reconstruction algorithm ill-posed. Prior to deep learning, the limited-view problem was addressed with complex hardware such as acoustic deflectors and full ring-shaped transducer arrays, as well as solutions like compressed sensing, weighted factor, and iterative filtered backprojection. The result of this ill-posed reconstruction is imaging artifacts that can be removed by CNNs. The deep learning algorithms used to remove limited-view artifacts include U-net and FD U-net, as well as generative adversarial networks (GANs) and volumetric versions of U-net. One GAN implementation of note improved upon U-net by using U-net as a generator and VGG as a discriminator, with the Wasserstein metric and gradient penalty to stabilize training (WGAN-GP). ==== Pixel-wise interpolation
Read more →
Huawei Member Center

Huawei Member Center is a benefits app which runs using Huawei Mobile Services. Originally launched in China, Huawei Member Center is now being developed primarily around devices such as P40 Pro and the Nova 7. == Membership Levels == The Huawei Member Center provides rewards in two primary ways, 1) device-specific & promotions and 2) via frequent use of Huawei products and apps, using points to redeem additional benefits. In China, Huawei members are already classified into three levels, the highest being “elite”. Membership level determines the level of perks received, from priority access to the service hotline, new device events & proprietary early-access opportunities. Huawei ran a number of member events in 2019 called "Huawei Member Day" to promote the Member Center including providing tips for the Mate 30 Pro and offering a 50Gb cloud storage upgrade to users. == HMC in China == Huawei Member Center Has seen significant adoption in China and the east, the rewards for use on the app have ranged from free book coupons, discounted travel and exclusive gifts of new devices, such as the Huawei Enjoy Z.
Read more →
Texture compression

Texture compression is a specialized form of image compression designed for storing texture maps in 3D computer graphics rendering systems. Unlike conventional image compression algorithms, texture compression algorithms are optimized for random access. Texture compression can be applied to reduce memory usage at runtime. Texture data is often the largest source of memory usage in a mobile application. == Tradeoffs == In their seminal paper on texture compression, Beers, Agrawala and Chaddha list four features that tend to differentiate texture compression from other image compression techniques. These features are: Decoding Speed It is highly desirable to be able to render directly from the compressed texture data and so, in order not to impact rendering performance, decompression must be fast. Random Access Since predicting the order that a renderer accesses texels would be difficult, any texture compression scheme must allow fast random access to decompressed texture data. This tends to rule out many better-known image compression schemes such as JPEG or run-length encoding. Compression Rate and Visual Quality In a rendering system, lossy compression can be more tolerable than for other use cases. Some texture compression libraries, such as crunch, allow the developer to flexibly trade off compression rate vs. visual quality, using methods such as rate–distortion optimization (RDO). Encoding Speed Texture compression is more tolerant of asymmetric encoding/decoding rates as the encoding process is often done only once during the application authoring process. Given the above, most texture compression algorithms involve some form of fixed-rate lossy vector quantization of small fixed-size blocks of pixels into small fixed-size blocks of coding bits, sometimes with additional extra pre-processing and post-processing steps. Block Truncation Coding is a very simple example of this family of algorithms. Because their data access patterns are well-defined, texture decompression may be executed on-the-fly during rendering as part of the overall graphics pipeline, reducing overall bandwidth and storage needs throughout the graphics system. As well as texture maps, texture compression may also be used to encode other kinds of rendering map, including bump maps and surface normal maps. Texture compression may also be used together with other forms of map processing such as mipmaps and anisotropic filtering. == Availability == Some examples of practical texture compression systems are S3 Texture Compression (S3TC), PVRTC, Ericsson Texture Compression (ETC) and Adaptive Scalable Texture Compression (ASTC); these may be supported by special function units in modern graphics processing units (GPUs). OpenGL and OpenGL ES, as implemented on many video accelerator cards and mobile GPUs, can support multiple common kinds of texture compression - generally through the use of vendor extensions. == Supercompression == A compressed-texture can be further compressed in what is called "supercompression". Fixed-rate texture compression formats are optimized for random access and are much less efficient compared to image formats such as PNG. By adding further compression, a programmer can reduce the efficiency gap. The extra layer can be decompressed by the CPU so that the GPU receives a normal compressed texture, or in newer methods, decompressed by the GPU itself. Supercompression saves the same amount of VRAM as regular texture compression, but saves more disk space and download size. == Neural Texture Compression == Random-Access Neural Compression of Material Textures (Neural Texture Compression) is a Nvidia's technology which enables two additional levels of detail (16× more texels, so four times higher resolution) while maintaining similar storage requirements as traditional texture compression methods. The key idea is compressing multiple material textures and their mipmap chains together, and using a small neural network, that is optimized for each material, to decompress them.
Read more →
SmarterChild

SmarterChild was a chatbot available on AOL Instant Messenger and Windows Live Messenger (previously MSN Messenger) networks. == History == SmarterChild was an apparently intelligent agent or "bot" developed by ActiveBuddy, Inc., with offices in New York and Sunnyvale. It was widely distributed across global instant messaging networks. SmarterChild became very popular, attracting over 30 million Instant Messenger "buddies" on AIM (AOL), MSN and Yahoo Messenger over the course of its lifetime. Founded in 2000, ActiveBuddy was the brainchild of Robert Hoffer and Timothy Kay, who later brought seasoned advertising executive Peter Levitan on board as CEO. The concept for conversational instant messaging bots came from the founder's vision to add natural language comprehension functionality to the increasingly popular AIM instant messaging application. The original implementation took shape as a demo that Kay programmed in Perl in his Los Altos garage to connect a single buddy name, "ActiveBuddy", to look up stock symbols, and later allow AIM users to play Colossal Cave Adventure, a word-based adventure game, and MIT's Boris Katz Start Question Answering System but quickly grew to include a wide range of database applications the company called 'knowledge domains' including instant access to news, weather, stock information, movie times, yellow pages listings, and detailed sports data, as well as a variety of tools (personal assistant, calculators, translator, etc.). None of the individual domains which the company had named “stocksBuddy”, “sportsBuddy”, etc. ever launched publicly. When Stephen Klein came on board as COO — and eventually CEO — he insisted that all of the disparate test “buddies” be launched together with the company’s highly-developed colloquial chat domain. He suggested using “SmarterChild”, a username coined by Tim Kay which Tim was using to test various things. The bundled domains were launched publicly as SmarterChild (on AIM initially) in June 2001. SmarterChild provided information wrapped in fun and quirky conversation. The company generated no revenue from SmarterChild, but used it as a demonstration of the power of what Klein called “conversational computing”. The company subsequently marketed Automated Service Agents—delivering immediate answers to customer service inquiries—-to large corporations, like Comcast, Cingular, TimeWarner Cable, etc. SmarterChild's popularity spawned targeted marketing-oriented bots for Radiohead, Austin Powers, Intel, Keebler, The Sporting News and others. ActiveBuddy co-founders, Kay and Hoffer, as co-inventors, were issued two controversial U.S. patents in 2002. ActiveBuddy changed its name to Colloquis (briefly Conversagent) and targeted development of consumer-facing enterprise customer service agents, which the company marketed as Automated Service Agents. Microsoft acquired Colloquis in October 2006 and proceeded to de-commission SmarterChild and kill off the Automated Service Agent business as well. Robert Hoffer, ActiveBuddy co-founder, licensed the technology from Microsoft after Microsoft abandoned the Colloquis technology.
Read more →
ClearForest

ClearForest was an Israeli software company that developed and marketed text analytics and text mining solutions. == History == Founded in 1998, ClearForest had its headquarters just outside Boston and a development center in Or Yehuda. The company was acquired by Reuters in April, 2007. It now markets its services under the names Calais, OpenCalais, and OneCalais. ClearForest was previously venture-backed; its last funding round was led by Greylock Ventures and closed in 2005. Other investors included DB Capital Partners, Pitango, Walden Israel, Booz Allen, JP Morgan Partners and HarbourVest Partners. On February 7, 2008 Reuters announced the launch of Open Calais, a named-entity recognition and semantic analysis service that uses ClearForest technology. On April 30, 2007, Reuters announced that it would acquire ClearForest. Sources estimate the acquisition to be for $25 Million. == Solutions and products == ClearForest offers several hosted solutions, including: OpenCalais, a free web service and open API (for commercial and non-commercial use) that performs named-entity recognition and enables automatic metadata generation using the ClearForest financial module. Semantic Web Services (SWS), an on-demand service that makes ClearForest's natural language processing tools available as a standard web service. A subset of ClearForest's capabilities is available via SWS at no cost. Gnosis, a free Firefox extension that uses SWS to analyze the content of a web page. Gnosis identifies named entities such as people, companies, organizations, geographies and products on the page being viewed. Gnosis also automatically processes pages from Wikipedia, providing additional links for people, geographies and other entities which were not explicitly linked within the subject article. Harvest, a real-time machine-readable news service that uses SWS to process a company's news and document feeds and return machine-readable information about people, companies, locations and over 200 other entities facts and events. ClearForest also offers Text Analytics solutions targeted at specific business problems, including: Equity valuation for hedge funds and alternative investments firms Metadata & database creation for publishers and information providers/services Tapping "voice of customer" for market and survey research firms Quality Early Warning for vehicle, capital equipment & durable goods manufacturers
Read more →
Sketch Engine

Sketch Engine is a corpus manager and text analysis software developed by Lexical Computing since 2003. Its purpose is to enable people studying language behaviour (lexicographers, researchers in corpus linguistics, translators or language learners) to search large text collections according to complex and linguistically motivated queries. Sketch Engine gained its name after one of the key features, word sketches: one-page, automatic, corpus-derived summaries of a word's grammatical and collocational behaviour. Currently, it supports and provides corpora in over 100 languages. == History of development == Sketch Engine is a product of Lexical Computing, a company founded in 2003 by the lexicographer and research scientist Adam Kilgarriff. He started a collaboration with Pavel Rychlý, a computer scientist working at the Natural Language Processing Centre, Masaryk University, and the developer of Manatee and Bonito (two major parts of the software suite). Kilgarriff also introduced the concept of word sketches. Since then, Sketch Engine has been commercial software, however, all the core features of Manatee and Bonito that were developed by 2003 (and extended since then) are freely available under the GPL license within the NoSketch Engine suite. == Features == A list of tools available in Sketch Engine: Word sketches – a one-page automatic derived summary of a word's grammatical and collocational behaviour Word sketch difference – compares and contrasts two words by analysing their collocations Distributional thesaurus – automated thesaurus for finding words with similar meaning or appearing in the same/similar context Concordance search – finds occurrences of a word form, lemma, phrase, tag or complex structure Collocation search – word co-occurrence analysis displaying the most frequent words (for a search word) which can be regarded as collocation candidates Word lists – generates frequency lists which can be filtered with complex criteria n-grams – generates frequency lists of multi-word expressions Terminology / Keyword extraction (both monolingual and bilingual) – automatic extraction of key words and multi-word terms from texts (based on frequency count and linguistic criteria) Diachronic analysis (Trends) – detecting words which undergo changes in the frequency of use in time (show trending words) Corpus building and management – create corpora from the Web or uploaded texts including part-of-speech tagging and lemmatization which can be used as data mining software Parallel corpus (bilingual) facilities – looking up translation examples (EUR-Lex corpus, Europarl corpus, OPUS corpus, etc.) or building a parallel corpus from own aligned texts Text type analysis – statistics of metadata in the corpus === Keywords and terminology extraction === Sketch Engine can perform automatic term extraction by identifying words typical of a particular corpus, document, or text. Single words and multi-word units can be extracted from monolingual or bilingual texts. The terminology extraction feature provides a list of relevant terms based on comparison with a large corpus of general language. This functionality is also available as a separate service called OneClick Terms with a dedicated interface. === SKELL === A free web service based on Sketch Engine and aimed at language learners and teachers is SKELL (formerly SkELL). It exploits Sketch Engine's proprietary GDEX (Good Dictionary Examples) scoring function to provide authentic example sentences for specific target words. Results are drawn from a special corpus of high-quality texts covering everyday, standard, formal, and professional language and displayed as a concordance. SKELL also includes simplified versions of Sketch Engine's word sketch and thesaurus functions. It has been suggested that SKELL can be used, for instance, to help students understand the meaning and/or usage of a word or phrase; to help teachers wanting to use example sentences in a class; to discover and explore collocates; to create gap-fill exercises; to teach various kinds of homonyms and polysemous words. SKELL was first presented in 2014, when only English was supported. Later, support was added for Russian, Czech, German, Italian and Estonian. == List of text corpora == Sketch Engine provides access to more than 800 text corpora. There are monolingual as well as multilingual corpora of different sizes (from one thousand words up to 85 billion words) and various sources (e.g. web, books, subtitles, legal documents). The list of corpora includes British National Corpus, Brown Corpus, Cambridge Academic English Corpus and Cambridge Learner Corpus, CHILDES corpora of child language, OpenSubtitles (a set of 60 parallel corpora), 24 multilingual corpora of EUR-Lex documents, the TenTen Corpus Family (multi-billion web corpora), and Trends corpora (monitor corpora with daily updates). == Architecture == Sketch Engine consists of three main components: an underlying database management system called Manatee, a web interface search front-end called Bonito, and a web interface for corpus building and management called Corpus Architect. === Manatee === Manatee is a database management system specifically devised for effective indexing of large text corpora. It is based on the idea of inverted indexing (keeping an index of all positions of a given word in the text). It has been used to index text corpora comprising tens of billions of words. Searching corpora indexed by Manatee is performed by formulating queries in the Corpus Query Language (CQL). Manatee is written in C++ and offers an API for a number of other programming languages including Python, Java, Perl and Ruby. Recently, it was rewritten into Go for faster processing of corpus queries. === Bonito === Bonito is a web interface for Manatee providing access to corpus search. In the client–server model, Manatee is the server and Bonito plays the client part. It is written in Python. === Corpus Architect === Corpus Architect is a web interface providing corpus building and management features. It is also written in Python. == Applications == Sketch Engine has been used by major British and other publishing houses for producing dictionaries such as Macmillan English Dictionary, Dictionnaires Le Robert, Oxford University Press or Shogakukan. Four of United Kingdom's five biggest dictionary publishers use Sketch Engine.
Read more →
Nextcloud

Nextcloud is a modular workspace platform designed to provide teams and businesses with a comprehensive environment for digital collaboration. Beyond central data management, it integrates office suites like Collabora Online and EuroOffice office suites. for seamless, cooperative workflows. The platform features built-in tools for chat, videoconferencing, and a privacy-focused AI assistant capable of running entirely on local LLMs. Supported by a rich ecosystem of apps, it can be hosted in the cloud or on premises and can scale up to millions of users. It has been translated into over 100 languages. == Features == Nextcloud files are stored in conventional directory structures, accessible via WebDAV if necessary. A SQLite, MySQL/MariaDB or PostgreSQL database is required to provide additional functionality like permissions, shares, and comments. Nextcloud can synchronize with local clients running Windows (Windows 8.1 and above), macOS (10.14 or later), Linux and FreeBSD. Nextcloud permits user and group administration locally or via different backends like OpenID or LDAP. Content can be shared inside the system by defining granular read/write permissions between users and groups. Nextcloud users can create public URLs when sharing files. Logging of file-related actions, as well as disallowing access based on file access rules is also available. Security options like brute-force protection and multi-factor authentication using TOTP, WebAuthn, Oauth2, and OpenID Connect are available. Nextcloud has planned new features such as monitoring capabilities, full-text search and Kerberos authentication, as well as audio/video conferencing, expanded federation and smaller user interface improvements. == History == In April 2016 Frank Karlitschek and most core contributors left ownCloud Inc. These included some of ownCloud's staff according to sources near to the ownCloud community. Karlitschek and many of these contributors went on to fork ownCloud, creating Nextcloud. The fork was preceded by a blog post of Karlitschek announcing his departure and raising questions about the management of the ownCloud, its community, and priorities between growth, money, and sustainability. There have been no official statements about the reason for the fork. However, Karlitschek mentioned the fork several times in a talk at the 2018 FOSDEM conference and in two appearances on the FLOSS Weekly podcast, emphasizing cultural mismatch between open source developers and business oriented people not used to the open source community. On June 2, within 12 hours of the announcement of the fork, the American entity "ownCloud Inc." announced that it is shutting down with immediate effect, stating that "[...] main lenders in the US have cancelled our credit. Following American law, we are forced to close the doors of ownCloud, Inc. with immediate effect and terminate the contracts of 8 employees." ownCloud Inc. accused Karlitschek of poaching developers, while Nextcloud developers such as Arthur Schiwon stated that he "decided to quit because not everything in the ownCloud Inc. company world evolved as I imagined". ownCloud GmbH continued operations, secured financing from new investors and took over the business of ownCloud Inc. In April 2018 Informationstechnikzentrum Bund (ITZBund) reported Nextcloud won the tender for "Bundescloud" (Germany government cloud) project. In August 2019 it was announced that the governments of France, Sweden and the Netherlands would use Nextcloud for file transfer. In January 2020 Nextcloud 18 "Nextcloud Hub" was released. The major change was direct integration with an Office suite (OnlyOffice) and Nextcloud announced that their goal was to compete with Office 365 and Google Docs. A partnership with Ionos was revealed – its hosting location in Germany and compliance with GDPR should support the goal of data sovereignty. In spring 2020 remote work and web conferencing usage increased due to the COVID-19 pandemic and Nextcloud released version 19 with chat and videoconferencing Talk app integrated into the application core. Communication with an optional "high performance back-end" allows self-hosting of web conferences with more than 10 participants. Collabora Online was introduced as another integrated office suite. In August 2021 Nextcloud was chosen as a collaboration platform for European cloud software GAIA-X. In a September 2021 European Commission report it was mentioned as "the most widely deployed Open Source content collaboration platform" Following the 2025 United States tariffs against the European Union, fear of overreliance on US cloud providers such as Microsoft 365 and Google Workspace increased, with Nextcloud being one of the foremost contenders to replace them. Some governmental organisations including the European Data Protection Supervisor and the German state of Schleswig-Holstein have since switched from Microsoft's Sharepoint to Nextcloud. According to Nextcloud, during the first 5 months of 2025, customer interest in the software had tripled.
Read more →
Virtual assistant

A virtual assistant (VA) is a software agent that can perform a range of tasks or services for a user based on user input, such as commands or questions, including verbal ones. Such technologies often incorporate chatbot capabilities to streamline task execution. The interaction may be via text, graphical interface, or voice, as some virtual assistants are able to interpret human speech and respond via synthesized voices. In many cases, users can ask their virtual assistants questions, control home automation devices and media playback, and manage other basic tasks such as email, to-do lists, and calendars – all with verbal commands. In recent years, prominent virtual assistants for direct consumer use have included Apple Siri, Amazon Alexa, Google Assistant (Gemini), Microsoft Copilot and Samsung Bixby. Also, companies in various industries often incorporate some kind of virtual assistant technology into their customer service or support. Into the 2020s, the emergence of artificial intelligence based chatbots, such as ChatGPT, has brought increased capability and interest to the field of virtual assistant products and services. == History == === Experimental decades: 1910s–1980s === Radio Rex was the first voice-activated toy, patented in 1916 and released in 1922. It was a wooden toy in the shape of a dog that would come out of its house when its name is called. In 1952, Bell Labs presented "Audrey", the Automatic Digit Recognition machine. It occupied a six-foot-high relay rack, consumed substantial power, had streams of cables and exhibited the myriad maintenance problems associated with complex vacuum-tube circuitry. It could recognize the fundamental units of speech, phonemes. It was limited to the accurate recognition of digits spoken by designated talkers. It could therefore be used for voice dialing, but in most cases, push-button dialing was cheaper and faster, rather than speaking the consecutive digits. Another early tool which was enabled to perform digital speech recognition was the IBM Shoebox voice-activated calculator, presented to the general public during the 1962 Seattle World's Fair after its initial market launch in 1961. This early computer, developed almost 20 years before the introduction of the first IBM Personal Computer in 1981, was able to recognize 16 spoken words and the digits 0 to 9. The first natural language processing computer program or the chatbot ELIZA was developed by MIT professor Joseph Weizenbaum in the 1960s. It was created to "demonstrate that the communication between man and machine was superficial". ELIZA used pattern matching and substitution methodology into scripted responses to simulate conversation, which gave an illusion of understanding on the part of the program. Weizenbaum's own secretary reportedly asked Weizenbaum to leave the room so that she and ELIZA could have a real conversation. Weizenbaum was surprised by this, later writing: "I had not realized ... that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people. This gave name to the ELIZA effect, the tendency to unconsciously assume computer behaviors are analogous to human behaviors; that is, anthropomorphisation, a phenomenon present in human interactions with virtual assistants. The next milestone in the development of voice recognition technology was achieved in the 1970s at the Carnegie Mellon University in Pittsburgh, Pennsylvania with substantial support of the United States Department of Defense and its DARPA agency, funded five years of a Speech Understanding Research program, aiming to reach a minimum vocabulary of 1,000 words. Companies and academia including IBM, Carnegie Mellon University (CMU) and Stanford Research Institute took part in the program. The result was "Harpy", it mastered about 1000 words, the vocabulary of a three-year-old and it could understand sentences. It could process speech that followed pre-programmed vocabulary, pronunciation, and grammar structures to determine which sequences of words made sense together, and thus reducing speech recognition errors. In 1986, Tangora was an upgrade of the Shoebox, it was a voice recognizing typewriter. Named after the world's fastest typist at the time, it had a vocabulary of 20,000 words and used prediction to decide the most likely result based on what was said in the past. IBM's approach was based on a hidden Markov model, which adds statistics to digital signal processing techniques. The method makes it possible to predict the most likely phonemes to follow a given phoneme. Still each speaker had to individually train the typewriter to recognize their voice, and pause between each word. In 1983, Gus Searcy invented the "Butler in a Box", an electronic voice home controller system. === Birth of smart virtual assistants: 1990s–2010s === In the 1990s, digital speech recognition technology became a feature of the personal computer with IBM, Philips and Lernout & Hauspie fighting for customers. Much later the market launch of the first smartphone IBM Simon in 1994 laid the foundation for smart virtual assistants as we know them today. In 1997, Dragon's NaturallySpeaking software could recognize and transcribe natural human speech without pauses between each word into a document at a rate of 100 words per minute. A version of Naturally Speaking is still available for download and it is still used today, for instance, by many doctors in the US and the UK to document their medical records. In 2001 Colloquis publicly launched SmarterChild, on platforms like AIM and MSN Messenger. While entirely text-based SmarterChild was able to play games, check the weather, look up facts, and converse with users to an extent. The first modern digital virtual assistant installed on a smartphone was Siri, which was introduced as a feature of the iPhone 4S on 4 October 2011. Apple Inc. developed Siri following the 2010 acquisition of Siri Inc., a spin-off of SRI International, which is a research institute financed by DARPA and the United States Department of Defense. Its aim was to aid in tasks such as sending a text message, making phone calls, checking the weather or setting up an alarm. Over time, it has developed to provide restaurant recommendations, search the internet, and provide driving directions. In November 2014, Amazon announced Alexa alongside the Echo. In 2016, Salesforce debuted Einstein, developed from a set of technologies underlying the Salesforce platform. Einstein was replaced by Agentforce, an agentic AI, in September 2024. In April 2017 Amazon released a service for building conversational interfaces for any type of virtual assistant or interface. === Large Language Models: 2020s-present === In the 2020s, artificial intelligence (AI) systems like ChatGPT have gained popularity for their ability to generate human-like responses to text-based conversations. In February 2020, Microsoft introduced its Turing Natural Language Generation (T-NLG), which was then the "largest language model ever published at 17 billion parameters." On November 30, 2022, ChatGPT was launched as a prototype and quickly garnered attention for its detailed responses and articulate answers across many domains of knowledge. The advent of ChatGPT and its introduction to the wider public increased interest and competition in the space. In February 2023, Google began introducing an experimental service called "Bard" which is based on its LaMDA program to generate text responses to questions asked based on information gathered from the web. While ChatGPT and other generalized chatbots based on the latest generative AI are capable of performing various tasks associated with virtual assistants, there are also more specialized forms of such technology that are designed to target more specific situations or needs. == Method of interaction == Virtual assistants work via: Text, including: online chat (especially in an instant messaging application or other application ), SMS text, e-mail or other text-based communication channel, for example Conversica's intelligent virtual assistants for business. Voice: for example with Amazon Alexa on Amazon Echo devices, Siri on an iPhone, Google Assistant on Google-enabled Android devices, or Bixby on Samsung devices. Images: some assistants, such as Google Assistant (which includes Google Lens) and Bixby on the Samsung Galaxy series, have the added capability of performing image processing to recognize objects in images. Many virtual assistants are accessible via multiple methods, offering versatility in how users can interact with them, whether through chat, voice commands, or other integrated technologies. Virtual assistants use natural language processing (NLP) to match user text or voice input to executable commands. Some continually learn using artificial intelligence techniques including machine learning and ambient intelligence. To activate a virtual assistant u
Read more →
Deep image prior

Deep image prior is a type of convolutional neural network used to enhance a given image with no prior training data other than the image itself. A neural network is randomly initialized and used as prior to solve inverse problems such as noise reduction, super-resolution, and inpainting. Image statistics are captured by the structure of a convolutional image generator rather than by any previously learned capabilities. == Method == === Background === Inverse problems such as noise reduction, super-resolution, and inpainting can be formulated as the optimization task x ∗ = m i n x E ( x ; x 0 ) + R ( x ) {\displaystyle x^{}=min_{x}E(x;x_{0})+R(x)} , where x {\displaystyle x} is an image, x 0 {\displaystyle x_{0}} a corrupted representation of that image, E ( x ; x 0 ) {\displaystyle E(x;x_{0})} is a task-dependent data term, and R(x) is the regularizer. Deep neural networks learn a generator/decoder x = f θ ( z ) {\displaystyle x=f_{\theta }(z)} which maps a random code vector z {\displaystyle z} to an image x {\displaystyle x} . The image corruption method used to generate x 0 {\displaystyle x_{0}} is selected for the specific application. === Specifics === In this approach, the R ( x ) {\displaystyle R(x)} prior is replaced with the implicit prior captured by the neural network (where R ( x ) = 0 {\displaystyle R(x)=0} for images that can be produced by a deep neural networks and R ( x ) = + ∞ {\displaystyle R(x)=+\infty } otherwise). This yields the equation for the minimizer θ ∗ = a r g m i n θ E ( f θ ( z ) ; x 0 ) {\displaystyle \theta ^{}=argmin_{\theta }E(f_{\theta }(z);x_{0})} and the result of the optimization process x ∗ = f θ ∗ ( z ) {\displaystyle x^{}=f_{\theta ^{}}(z)} . The minimizer θ ∗ {\displaystyle \theta ^{}} (typically a gradient descent) starts from a randomly initialized parameters and descends into a local best result to yield the x ∗ {\displaystyle x^{}} restoration function. ==== Overfitting ==== A parameter θ may be used to recover any image, including its noise. However, the network is reluctant to pick up noise because it contains high impedance while useful signal offers low impedance. This results in the θ parameter approaching a good-looking local optimum so long as the number of iterations in the optimization process remains low enough not to overfit data. === Deep Neural Network Model === Typically, the deep neural network model for deep image prior uses a U-Net like model without the skip connections that connect the encoder blocks with the decoder blocks. The authors in their paper mention that "Our findings here (and in other similar comparisons) seem to suggest that having deeper architecture is beneficial, and that having skip-connections that work so well for recognition tasks (such as semantic segmentation) is highly detrimental." == Applications == === Denoising === The principle of denoising is to recover an image x {\displaystyle x} from a noisy observation x 0 {\displaystyle x_{0}} , where x 0 = x + ϵ {\displaystyle x_{0}=x+\epsilon } . The distribution ϵ {\displaystyle \epsilon } is sometimes known (e.g.: profiling sensor and photon noise) and may optionally be incorporated into the model, though this process works well in blind denoising. The quadratic energy function E ( x , x 0 ) = | | x − x 0 | | 2 {\displaystyle E(x,x_{0})=||x-x_{0}||^{2}} is used as the data term, plugging it into the equation for θ ∗ {\displaystyle \theta ^{}} yields the optimization problem m i n θ | | f θ ( z ) − x 0 | | 2 {\displaystyle min_{\theta }||f_{\theta }(z)-x_{0}||^{2}} . === Super-resolution === Super-resolution is used to generate a higher resolution version of image x. The data term is set to E ( x ; x 0 ) = | | d ( x ) − x 0 | | 2 {\displaystyle E(x;x_{0})=||d(x)-x_{0}||^{2}} where d(·) is a downsampling operator such as Lanczos that decimates the image by a factor t. === Inpainting === Inpainting is used to reconstruct a missing area in an image x 0 {\displaystyle x_{0}} . These missing pixels are defined as the binary mask m ∈ { 0 , 1 } H × V {\displaystyle m\in \{0,1\}^{H\times V}} . The data term is defined as E ( x ; x 0 ) = | | ( x − x 0 ) ⊙ m | | 2 {\displaystyle E(x;x_{0})=||(x-x_{0})\odot m||^{2}} (where ⊙ {\displaystyle \odot } is the Hadamard product). The intuition behind this is that the loss is computed only on the known pixels in the image, and the network is going to learn enough about the image to fill in unknown parts of the image even though the computed loss doesn't include those pixels. This strategy is used to remove image watermarks by treating the watermark as missing pixels in the image. === Flash–no-flash reconstruction === This approach may be extended to multiple images. A straightforward example mentioned by the author is the reconstruction of an image to obtain natural light and clarity from a flash–no-flash pair. Video reconstruction is possible but it requires optimizations to take into account the spatial differences. == Implementations == A reference implementation rewritten in Python 3.6 with the PyTorch 0.4.0 library was released by the author under the Apache 2.0 license: deep-image-prior A TensorFlow-based implementation written in Python 2 and released under the CC-SA 3.0 license: deep-image-prior-tensorflow A Keras-based implementation written in Python 2 and released under the GPLv3: machine_learning_denoising == Example == See Astronomy Picture of the Day (APOD) of 2024-02-18
Read more →