AI Analytical Thinking

AI Analytical Thinking — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Trebel (music app)

  Trebel is an on-demand music download and discovery platform developed by M&M Media Inc. The company's business model aims to combat digital music piracy by giving users access to on-demand music at no cost while delivering fair compensation to artists and music rights holders. Trebel has a patent that allows it to market itself as the only international music service in which users can legally download music and listen to it offline for free. As of March 2023, Trebel has a catalog of 75 million songs from record labels such as Universal Music Group, Sony Music Entertainment, Warner Music Group and hundreds of independent labels. Trebel is based in Stamford, Connecticut. with additional locations in Mexico City, Jakarta, Bogota, Los Angeles and Miami. The app is available in the Apple App Store, Google Play Store, and Huawei AppGallery. == History == Trebel was founded in 2014 by Gary Mekikian, who was previously the co-founder of answerFriend, Inc., which commercialized web based question-answering technologies and merged with Electric Knowledge, forming InQuira. This company was eventually acquired by Oracle Corporation in 2011. His co-founders at Trebel include Stanford classmates Corey Jones and Luis Soto Durazo, as well as his daughters Grace and Juliette. Mekikian envisioned Trebel as an alternative to music piracy after a high school classmate of his daughters was targeted by cyberattackers while illegally downloading music online. Trebel was initially released in 2015 under the name Project Carmen to students at Ohio State, Santa Monica College, Cal State Fullerton, UCLA and Long Beach State. In its original incarnation, the service planned to target students at 3,000 universities and 30,000 high schools in the United States. A beta version of the app was introduced in 2016 with content from Universal Music Group and Warner Music Group. Trebel launched commercially in the United States and Mexico in 2018. In 2018, Mexican mass-media corporation Televisa also became a minority investor in Trebel. In May 2020, during the early months of the COVID-19 pandemic, Trebel was a digital broadcast partner for Se Agradece, a concert produced in Mexico by Televisa to honor frontline COVID workers that featured artists such as Rosalia, J Balvin, Maluma and Ricky Martin. In June 2021, Trebel reached 3 million monthly active users. In October 2021, Trebel signed a music licensing agreement with Merlin Network, the licensing agency for the independent music sector that controls an estimated 12% of the global digital recorded music market. In January 2022, Trebel announced a strategic alliance with MNC Corporation, an Indonesian media conglomerate, which also became a minority backer of the company. In March 2022, Trebel reported 5.2 million monthly active users as a result of growth in Latin America. In the same month,, Latin music star Maluma became a backer of Trebel and an advisor to Gary Mekikian, helping expand the service throughout Latin America. On April 18, 2022, Trebel launched in Indonesia during the finale of the music competition show X Factor Indonesia. Trebel also signed a deal that month with Soccer Media Solutions, a sports and entertainment marketing agency in Mexico, to sell Trebel’s premium advertising inventory through Soccer Media. In May 2022, Guillermo Ochoa, goalkeeper for the Mexican national soccer team, invested in Trebel and became an ambassador for the company. On October 2, 2022, Trebel collaborated with Musica Studios, one of the largest music companies in Indonesia, on the production of a music festival in Jakarta titled Trebel Music Fest. The event featured performances by top Indonesian music artists such as Noah, Nidji, and d'Masiv. In October 2022, Trebel launched in Colombia. The service reached 1.2 million monthly active users in Colombia six months after launching. In December 2022, Trebel collaborated with KFC in Indonesia on the release of a KFC digital music program using a product called Trebel Max. As part of the program, KFC customers who bought the Crazy Superstar Combo package at KFC received a subscription to Trebel Max for 30 days. Trebel announced the launch of Trebel AI in May 2023. Trebel AI uses ChatGPT-powered technology to generate playlists based on natural language queries from users. In Indonesia, the Trebel AI feature was announced during a broadcast of the show Indonesian Idol XII that took place on May 8, 2023. In July 2023, Trebel reached more than 13 million monthly active users. In November 2023, Trebel became a featured app on the Discord app directory. Discord users that add the Trebel bot to their servers have access to Trebel's on-demand music library and have the exclusive privilege of being DJ's during server sessions with up to 150 concurrent listeners. == Platform == === Features === Trebel has a patent that allows it to market itself as the only international music service in which users can legally download music and listen to it offline for free. As of March 2023, Trebel has a catalog of 75 million songs from record labels such as Universal Music Group, Sony Music Entertainment, Warner Music Group and hundreds of independent labels. Trebel offers unlimited music downloads that are playable in the app by registered users only. Offline listening is free to all users and not blocked by a paywall. Users can search for music based on song, artist, album, browsing friends' recent activity, and through other users' playlists. The app also offers free cloud storage for downloaded songs. Trebel also contains a feature called SongID, which identifies music being played nearby using a short sample, then offers it for download on the service. Podcasts are available for free listening on the service as well. === Business model === Trebel uses a business model that generates revenue from the sale of digital advertising as well as user interactions with branded experiences, and consumption of virtual goods within the app (akin to mobile games). The app also features a brand takeover feature called Trebel Max, which offers unlimited access in exchange for users engaging with experiences offered by specific brands. Trebel’s brand partners include Uber, KFC, Walmart, Coca-Cola, Amazon and P&G. === Content === In September 2022, Trebel secured an exclusive release of the song “Suara Hatiku” by Indonesian actress Amanda Monopo. As of March 2023, Trebel offers 75 million songs through licensing agreements with Universal Music Group, Sony Music Entertainment, Warner Music Group and global indie rights agency Merlin. == Awards == In 2023, Trebel won three Google Play awards including "Best App of 2023", "Best Everyday Essentials" and "Users' Choice".

  Read more →
• 

  Autoencoder

  An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction, to generate lower-dimensional embeddings for subsequent use by other machine learning algorithms. Variants exist which aim to make the learned representations assume useful properties. Examples are regularized autoencoders (sparse, denoising and contractive autoencoders), which are effective in learning representations for subsequent classification tasks, and variational autoencoders, which can be used as generative models. Autoencoders are applied to many problems, including facial recognition, feature detection, anomaly detection, and learning the meaning of words. In terms of data synthesis, autoencoders can also be used to randomly generate new data that is similar to the input (training) data. == Mathematical principles == === Definition === An autoencoder is defined by the following components: Two sets: the space of encoded messages Z {\displaystyle {\mathcal {Z}}} ; the space of decoded messages X {\displaystyle {\mathcal {X}}} . Typically X {\displaystyle {\mathcal {X}}} and Z {\displaystyle {\mathcal {Z}}} are Euclidean spaces, that is, X = R m , Z = R n {\displaystyle {\mathcal {X}}=\mathbb {R} ^{m},{\mathcal {Z}}=\mathbb {R} ^{n}} with m > n . {\displaystyle m>n.} Two parametrized families of functions: the encoder family E ϕ : X → Z {\displaystyle E_{\phi }:{\mathcal {X}}\rightarrow {\mathcal {Z}}} , parametrized by ϕ {\displaystyle \phi } ; the decoder family D θ : Z → X {\displaystyle D_{\theta }:{\mathcal {Z}}\rightarrow {\mathcal {X}}} , parametrized by θ {\displaystyle \theta } .For any x ∈ X {\displaystyle x\in {\mathcal {X}}} , we usually write z = E ϕ ( x ) {\displaystyle z=E_{\phi }(x)} , and refer to it as the code, the latent variable, latent representation, latent vector, etc. Conversely, for any z ∈ Z {\displaystyle z\in {\mathcal {Z}}} , we usually write x ′ = D θ ( z ) {\displaystyle x'=D_{\theta }(z)} , and refer to it as the (decoded) message. Usually, both the encoder and the decoder are defined as multilayer perceptrons (MLPs). For example, a one-layer-MLP encoder E ϕ {\displaystyle E_{\phi }} is: E ϕ ( x ) = σ ( W x + b ) {\displaystyle E_{\phi }(\mathbf {x} )=\sigma (Wx+b)} where σ {\displaystyle \sigma } is an element-wise activation function, W {\displaystyle W} is a "weight" matrix, and b {\displaystyle b} is a "bias" vector. === Training an autoencoder === An autoencoder, by itself, is simply a tuple of two functions. To judge its quality, we need a task. A task is defined by a reference probability distribution μ r e f {\displaystyle \mu _{ref}} over X {\displaystyle {\mathcal {X}}} , and a "reconstruction quality" function d : X × X → [ 0 , ∞ ] {\displaystyle d:{\mathcal {X}}\times {\mathcal {X}}\to [0,\infty ]} , such that d ( x , x ′ ) {\displaystyle d(x,x')} measures how much x ′ {\displaystyle x'} differs from x {\displaystyle x} . With those, we can define the loss function for the autoencoder as L ( θ , ϕ ) := E x ∼ μ r e f [ d ( x , D θ ( E ϕ ( x ) ) ) ] {\displaystyle L(\theta ,\phi ):=\mathbb {\mathbb {E} } _{x\sim \mu _{ref}}[d(x,D_{\theta }(E_{\phi }(x)))]} The optimal autoencoder for the given task ( μ r e f , d ) {\displaystyle (\mu _{ref},d)} is then arg ⁡ min θ , ϕ L ( θ , ϕ ) {\displaystyle \arg \min _{\theta ,\phi }L(\theta ,\phi )} . The search for the optimal autoencoder can be accomplished by any mathematical optimization technique, but usually by gradient descent. This search process is referred to as "training the autoencoder". In most situations, the reference distribution is just the empirical distribution given by a dataset { x 1 , . . . , x N } ⊂ X {\displaystyle \{x_{1},...,x_{N}\}\subset {\mathcal {X}}} , so that μ r e f = 1 N ∑ i = 1 N δ x i {\displaystyle \mu _{ref}={\frac {1}{N}}\sum _{i=1}^{N}\delta _{x_{i}}} where δ x i {\displaystyle \delta _{x_{i}}} is the Dirac measure, the quality function is just L 2 {\displaystyle L^{2}} loss: d ( x , x ′ ) = ‖ x − x ′ ‖ 2 2 {\displaystyle d(x,x')=\|x-x'\|_{2}^{2}} , and ‖ ⋅ ‖ 2 {\displaystyle \|\cdot \|_{2}} is the Euclidean norm. Then the problem of searching for the optimal autoencoder is just a least-squares optimization: min θ , ϕ L ( θ , ϕ ) , where L ( θ , ϕ ) = 1 N ∑ i = 1 N ‖ x i − D θ ( E ϕ ( x i ) ) ‖ 2 2 {\displaystyle \min _{\theta ,\phi }L(\theta ,\phi ),\qquad {\text{where }}L(\theta ,\phi )={\frac {1}{N}}\sum _{i=1}^{N}\|x_{i}-D_{\theta }(E_{\phi }(x_{i}))\|_{2}^{2}} === Interpretation === An autoencoder has two main parts: an encoder that maps the message to a code, and a decoder that reconstructs the message from the code. An optimal autoencoder would perform as close to perfect reconstruction as possible, with "close to perfect" defined by the reconstruction quality function d {\displaystyle d} . The simplest way to perform the copying task perfectly would be to duplicate the signal. To suppress this behavior, the code space Z {\displaystyle {\mathcal {Z}}} usually has fewer dimensions than the message space X {\displaystyle {\mathcal {X}}} . Such an autoencoder is called undercomplete. It can be interpreted as compressing the message, or reducing its dimensionality. At the limit of an ideal undercomplete autoencoder, every possible code z {\displaystyle z} in the code space is used to encode a message x {\displaystyle x} that really appears in the distribution μ r e f {\displaystyle \mu _{ref}} , and the decoder is also perfect: D θ ( E ϕ ( x ) ) = x {\displaystyle D_{\theta }(E_{\phi }(x))=x} . This ideal autoencoder can then be used to generate messages indistinguishable from real messages, by feeding its decoder arbitrary code z {\displaystyle z} and obtaining D θ ( z ) {\displaystyle D_{\theta }(z)} , which is a message that really appears in the distribution μ r e f {\displaystyle \mu _{ref}} . If the code space Z {\displaystyle {\mathcal {Z}}} has dimension larger than (overcomplete), or equal to, the message space X {\displaystyle {\mathcal {X}}} , or the hidden units are given enough capacity, an autoencoder can learn the identity function and become useless. However, experimental results found that overcomplete autoencoders might still learn useful features. In the ideal setting, the code dimension and the model capacity could be set on the basis of the complexity of the data distribution to be modeled. A standard way to do so is to add modifications to the basic autoencoder, to be detailed below. == Variations == === Variational autoencoder (VAE) === Variational autoencoders (VAEs) belong to the families of variational Bayesian methods. Despite the architectural similarities with basic autoencoders, VAEs are architected with different goals and have a different mathematical formulation. The latent space is, in this case, composed of a mixture of distributions instead of fixed vectors. Given an input dataset x {\displaystyle x} characterized by an unknown probability function P ( x ) {\displaystyle P(x)} and a multivariate latent encoding vector z {\displaystyle z} , the objective is to model the data as a distribution p θ ( x ) {\displaystyle p_{\theta }(x)} , with θ {\displaystyle \theta } defined as the set of the network parameters so that p θ ( x ) = ∫ z p θ ( x , z ) d z {\displaystyle p_{\theta }(x)=\int _{z}p_{\theta }(x,z)dz} . === Sparse autoencoder (SAE) === Inspired by the sparse coding hypothesis in neuroscience, sparse autoencoders (SAE) are variants of autoencoders, such that the codes E ϕ ( x ) {\displaystyle E_{\phi }(x)} for messages tend to be sparse codes, that is, E ϕ ( x ) {\displaystyle E_{\phi }(x)} is close to zero in most entries. Sparse autoencoders may include more (rather than fewer) hidden units than inputs, but only a small number of the hidden units are allowed to be active at the same time. Encouraging sparsity improves performance on classification tasks. There are two main ways to enforce sparsity. One way is to simply clamp all but the highest-k activations of the latent code to zero. This is the k-sparse autoencoder. The k-sparse autoencoder inserts the following "k-sparse function" in the latent layer of a standard autoencoder: f k ( x 1 , . . . , x n ) = ( x 1 b 1 , . . . , x n b n ) {\displaystyle f_{k}(x_{1},...,x_{n})=(x_{1}b_{1},...,x_{n}b_{n})} where b i = 1 {\displaystyle b_{i}=1} if | x i | {\displaystyle |x_{i}|} ranks in the top k, and 0 otherwise. Backpropagating through f k {\displaystyle f_{k}} is simple: set gradient to 0 for b i = 0 {\displaystyle b_{i}=0} entries, and keep gradient for b i = 1 {\displaystyle b_{i}=1} entries. This is essentially a generalized ReLU function. The other way is a relaxed version of the k-

  Read more →
• 

  Memetic algorithm

  In computer science and operations research, a memetic algorithm (MA) is an extension of an evolutionary algorithm (EA) that aims to accelerate the evolutionary search for the optimum. An EA is a metaheuristic that reproduces the basic principles of biological evolution as a computer algorithm in order to solve challenging optimization or planning tasks, at least approximately. An MA uses one or more suitable heuristics or local search techniques to improve the quality of solutions generated by the EA and to speed up the search. The effects on the reliability of finding the global optimum depend on both the use case and the design of the MA. Memetic algorithms represent one of the recent growing areas of research in evolutionary computation. The term MA is now widely used as a synergy of evolutionary or any population-based approach with separate individual learning or local improvement procedures for problem search. Quite often, MAs are also referred to in the literature as Baldwinian evolutionary algorithms, Lamarckian EAs, cultural algorithms, or genetic local search. == Introduction == Inspired by both Darwinian principles of natural evolution and Dawkins' notion of a meme, the term memetic algorithm (MA) was introduced by Pablo Moscato in his technical report in 1989 where he viewed MA as being close to a form of population-based hybrid genetic algorithm (GA) coupled with an individual learning procedure capable of performing local refinements. The metaphorical parallels, on the one hand, to Darwinian evolution and, on the other hand, between memes and domain specific (local search) heuristics are captured within memetic algorithms thus rendering a methodology that balances well between generality and problem specificity. This two-stage nature makes them a special case of dual-phase evolution. The basic idea behind an MA is to combine the advantages of a global search performed by an EA (or another global search method) with the local refinement provided by one or more local search techniques, while avoiding their drawbacks. The main disadvantage of EAs is that, when searching in the vicinity of an optimum, they perform poorly in determining the exact position of that optimum. The downside of local search methods lies simply in the locality of their search relative to the chosen starting point. The combination of these two classes of methods aims to merge global and local search so that the advantages of both approaches can be leveraged. The idea of this approach can be illustrated by the search for the highest mountain in the Alps. A local search method would climb one of the mountains near the starting point, ignoring Mont Blanc as long as the starting point is not in its vicinity. An EA, on the other hand, will likely only find Mont Blanc after examining many other mountains, valleys, and hills, and then it will have difficulty identifying the summit cross. From the perspective of an MA’s global search procedure, however, only the summits of hills and mountains are seen, and its search is limited to finding the best summit. The open question is whether the additional effort required for the local search is worthwhile. This depends not only on the design of the MA but also on the specific application and the local search methods used. In the context of complex optimization, many different instantiations of memetic algorithms have been reported across a wide range of application domains, in general, converging to high-quality solutions more efficiently than their conventional evolutionary counterparts. In general, using the ideas of memetics within a computational framework is called memetic computing or memetic computation (MC). With MC, the traits of universal Darwinism are more appropriately captured. Viewed in this perspective, MA is a more constrained notion of MC. More specifically, MA covers one area of MC, in particular dealing with areas of evolutionary algorithms that marry other deterministic refinement techniques for solving optimization problems. MC extends the notion of memes to cover conceptual entities of knowledge-enhanced procedures or representations. == Theoretical Background == The no-free-lunch theorems of optimization and search state that all optimization strategies are equally effective with respect to the set of all optimization problems. Conversely, this means that one can expect the following: The more efficiently an algorithm solves a problem or class of problems, the less general it is and the more problem-specific knowledge it builds on. This insight leads directly to the recommendation to complement generally applicable metaheuristics with application-specific methods or heuristics, which fits well with the concept of MAs. == The development of MAs == === 1st generation === Pablo Moscato characterized an MA as follows: "Memetic algorithms are a marriage between a population-based global search and the heuristic local search made by each of the individuals. ... The mechanisms to do local search can be to reach a local optimum or to improve (regarding the objective cost function) up to a predetermined level." And he emphasizes "I am not constraining an MA to a genetic representation.". This original definition of MA although encompasses characteristics of cultural evolution (in the form of local refinement) in the search cycle, it may not qualify as a true evolving system according to universal Darwinism, since all the core principles of inheritance/memetic transmission, variation, and selection are missing. This suggests why the term MA stirred up criticisms and controversies among researchers when first introduced. The following pseudo code would correspond to this general definition of an MA: Pseudo code Procedure Memetic Algorithm Initialize: Generate an initial population, evaluate the individuals and assign a quality value to them; while Stopping conditions are not satisfied do Evolve a new population using stochastic search operators. Evaluate all individuals in the population and assign a quality value to them. Select the subset of individuals, Ω i l {\displaystyle \Omega _{il}} , that should undergo the individual improvement procedure. for each individual in Ω i l {\displaystyle \Omega _{il}} do Perform individual learning using meme(s) with frequency or probability of f i l {\displaystyle f_{il}} , with an intensity of t i l {\displaystyle t_{il}} . Proceed with Lamarckian or Baldwinian learning. end for end while Lamarckian learning in this context means to update the chromosome according to the improved solution found by the individual learning step, while Baldwinian learning leaves the chromosome unchanged and uses only the improved fitness. This pseudo code leaves open which steps are based on the fitness of the individuals and which are not. In question are the evolving of the new population and the selection of Ω i l {\displaystyle \Omega _{il}} . Since most MA implementations are based on EAs, the pseudo code of a corresponding representative of the first generation is also given here, following Krasnogor: Pseudo code Procedure Memetic Algorithm Based on an EA Initialization: t = 0 {\displaystyle t=0} ; // Initialization of the generation counter Randomly generate an initial population P ( t ) {\displaystyle P(t)} ; Compute the fitness f ( p ) ∀ p ∈ P ( t ) {\displaystyle f(p)\ \ \forall p\in P(t)} ; while Stopping conditions are not satisfied do Selection: Accordingly to f ( p ) {\displaystyle f(p)} choose a subset of P ( t ) {\displaystyle P(t)} and store it in M ( t ) {\displaystyle M(t)} ; Offspring: Recombine and mutate individuals p ∈ M ( t ) {\displaystyle p\in M(t)} and store them in M ′ ( t ) {\displaystyle M'(t)} ; Learning: Improve p ′ {\displaystyle p'} by local search or heuristic ∀ p ′ ∈ M ′ ( t ) {\displaystyle \forall p'\in M'(t)} ; Evaluation: Compute the fitness f ( p ′ ) ∀ p ′ ∈ M ′ ( t ) {\displaystyle f(p')\ \ \forall p'\in M'(t)} ; if Lamarckian learning then Update chromosome of p ′ {\displaystyle p'} according to improvement ∀ p ′ ∈ M ′ ( t ) {\displaystyle \forall p'\in M'(t)} ; fi New generation: Generate P ( t + 1 ) {\displaystyle P(t+1)} by selecting some individuals from P ( t ) {\displaystyle P(t)} and M ′ ( t ) {\displaystyle M'(t)} ; t = t + 1 {\displaystyle t=t+1} ; // Increment the generation counter end while Return best individual p ∈ P ( t − 1 ) {\displaystyle p\in P(t-1)} as result; There are some alternatives for this MA scheme. For example: All or some of the initial individuals may be improved by the meme(s). The parents may be locally improved instead of the offspring. Instead of all offspring, only a randomly selected or fitness-dependent fraction may undergo local improvement. The latter requires the evaluation of the offspring in M ′ ( t ) {\displaystyle M'(t)} prior to the Learning step. === 2nd generation === Multi-meme, hyper-heuristic and meta-Lamarckian MA are referred to as second generation MA exhibiting the principles of me

  Read more →
• 

  Multilinear subspace learning

  Multilinear subspace learning is an approach for disentangling the causal factor of data formation and performing dimensionality reduction. The Dimensionality reduction can be performed on a data tensor that contains a collection of observations that have been vectorized, or observations that are treated as matrices and concatenated into a data tensor. Here are some examples of data tensors whose observations are vectorized or whose observations are matrices concatenated into data tensor images (2D/3D), video sequences (3D/4D), and hyperspectral cubes (3D/4D). The mapping from a high-dimensional vector space to a set of lower dimensional vector spaces is a multilinear projection. When observations are retained in the same organizational structure as matrices or higher order tensors, their representations are computed by performing linear projections into the column space, row space and fiber space. Multilinear subspace learning algorithms are higher-order generalizations of linear subspace learning methods such as principal component analysis (PCA), independent component analysis (ICA), linear discriminant analysis (LDA) and canonical correlation analysis (CCA). == Background == Multilinear methods may be causal in nature and perform causal inference, or they may be simple regression methods from which no causal conclusion are drawn. Linear subspace learning algorithms are traditional dimensionality reduction techniques that are well suited for datasets that are the result of varying a single causal factor. Unfortunately, they often become inadequate when dealing with datasets that are the result of multiple causal factors. . Multilinear subspace learning can be applied to observations whose measurements were vectorized and organized into a data tensor for causally aware dimensionality reduction. These methods may also be employed in reducing horizontal and vertical redundancies irrespective of the causal factors when the observations are treated as a "matrix" (ie. a collection of independent column/row observations) and concatenated into a tensor. == Algorithms == === Multilinear principal component analysis === Historically, multilinear principal component analysis has been referred to as "M-mode PCA", a terminology which was coined by Peter Kroonenberg. In 2005, Vasilescu and Terzopoulos introduced the Multilinear PCA terminology as a way to better differentiate between multilinear tensor decompositions that computed 2nd order statistics associated with each data tensor mode, and subsequent work on Multilinear Independent Component Analysis that computed higher order statistics for each tensor mode. MPCA is an extension of PCA. === Multilinear independent component analysis === Multilinear independent component analysis is an extension of ICA. === Multilinear linear discriminant analysis === Multilinear extension of LDA TTP-based: Discriminant Analysis with Tensor Representation (DATER) TTP-based: General tensor discriminant analysis (GTDA) TVP-based: Uncorrelated Multilinear Discriminant Analysis (UMLDA) === Multilinear canonical correlation analysis === Multilinear extension of CCA TTP-based: Tensor Canonical Correlation Analysis (TCCA) TVP-based: Multilinear Canonical Correlation Analysis (MCCA) TVP-based: Bayesian Multilinear Canonical Correlation Analysis (BMTF) A TTP is a direct projection of a high-dimensional tensor to a low-dimensional tensor of the same order, using N projection matrices for an Nth-order tensor. It can be performed in N steps with each step performing a tensor-matrix multiplication (product). The N steps are exchangeable. This projection is an extension of the higher-order singular value decomposition (HOSVD) to subspace learning. Hence, its origin is traced back to the Tucker decomposition in 1960s. A TVP is a direct projection of a high-dimensional tensor to a low-dimensional vector, which is also referred to as the rank-one projections. As TVP projects a tensor to a vector, it can be viewed as multiple projections from a tensor to a scalar. Thus, the TVP of a tensor to a P-dimensional vector consists of P projections from the tensor to a scalar. The projection from a tensor to a scalar is an elementary multilinear projection (EMP). In EMP, a tensor is projected to a point through N unit projection vectors. It is the projection of a tensor on a single line (resulting a scalar), with one projection vector in each mode. Thus, the TVP of a tensor object to a vector in a P-dimensional vector space consists of P EMPs. This projection is an extension of the canonical decomposition, also known as the parallel factors (PARAFAC) decomposition. === Typical approach in MSL === There are N sets of parameters to be solved, one in each mode. The solution to one set often depends on the other sets (except when N=1, the linear case). Therefore, the suboptimal iterative procedure in is followed. Initialization of the projections in each mode For each mode, fixing the projection in all the other mode, and solve for the projection in the current mode. Do the mode-wise optimization for a few iterations or until convergence. This is originated from the alternating least square method for multi-way data analysis. == Code == MATLAB Tensor Toolbox by Sandia National Laboratories. The MPCA algorithm written in Matlab (MPCA+LDA included). The UMPCA algorithm written in Matlab (data included). The UMLDA algorithm written in Matlab (data included). == Tensor data sets == 3D gait data (third-order tensors): 128x88x20(21.2M); 64x44x20(9.9M); 32x22x10(3.2M);

  Read more →
• 

  CityEngine

  ArcGIS CityEngine is a commercial 3D modeling program. Developed by Esri R&D Center Zurich (formerly Procedural Inc.), it specializes in the generation of 3D urban environments to support the creation of detailed large-scale 3D city models. Unlike traditional 3D modeling methodology, which uses computer-aided design (CAD) tools and techniques, CityEngine takes a procedural modeling approach which shapes generation via a rules-based system. Due to its integration with the wider ArcGIS platform, CityEngine can also be used with geographic information system (GIS) datasets. CityEngine can be used for urban planning and architecture, graphics visualization, game development, entertainment, and archeology. CityEngine can be used to visualize the building information modeling (BIM) data of buildings in a larger urban context, making for more realistic construction projects. == History and releases == === Software history === ArcGIS CityEngine, originally named Esri CityEngine, was developed at Swiss technology university ETH Zurich by Pascal Mueller, the co-founder and CEO of Procedural Inc. While researching for his PhD at the ETH Computer Vision Lab, Mueller invented a number of techniques for procedural modeling of 3D architecture that make up the foundation of CityEngine. CityEngine publically debuted at the 2001 SIGGRAPH conference; since then, additional research papers have been published that have contributed to CityEngine and its features. The first commercial version of CityEngine was released in 2008. In 2007, Procedural Inc. was founded and separated from ETH Zurich, the top-ranking technology university in Switzerland. In the summer of 2011, Procedural Inc. was acquired by Esri Inc., becoming Esri R&D Center Zurich. Esri CityEngine was renamed to ArcGIS CityEngine in June 2020 to offically make it a part of the ArcGIS software suite. === Releases === === Licensing and pricing === ArcGIS CityEngine is included in the Professional and Professional Plus tiers of ArcGIS Online. Pricing may vary by region and distributors. In the US, the professional tier costs US$2,200 per year; in the UK, it is £4,200 per year (excluding VAT). CityEngine can be purchased elsewhere via a local Esri partner. . Once purchased, users can download and obtain license details from the MyEsri portal. == Features == CGA (computer generated architecture) parametric modeling rules to control mass, geometry assets, proportions, or texturing of buildings or streets on a citywide scale Select a target location and import geo-referenced satellite imagery and 3D terrain of the location to more quickly build accurate urban environments through OpenStreetMap integration Interactively control specific street or building parameters, such as height or age Import/export geo-spatial/vector data with industry-standard formats such as Esri Shapefile, File Geodatabase, and OpenStreetMap, as well as file formats for WebGL, KMZ, Collada, Autodesk FBX, Autodesk Maya, 3DS, Wavefront OBJ, RenderMan RIB, Alembic, e-on software's Vue, Universal Scene Description USD, Khronos Group GLTF, Unreal Engine, and Unreal Datasmith Script and generate rules-based reports to show socioeconomic figures (e.g., Gross Floor Area (GFA) and Floor Area Ratio (FAR)) to analyze their urban design proposals. VR viewing of modeled environments with Samsung Gear VR Use a variety of materials through the Esri materials library == Procedural modeling == ArcGIS CityEngine uses a procedural modeling approach to automatically generate models through a predefined rule set. The rules are defined through a CGA shape grammar system, enabling the creation of complex parametric models. Users can change or add the shape grammar as needed. Urban environments can be modeled within CityEngine by starting with creating a street network (either from the street drawing tool or with data imported from map data). Then, lots may be subdivided as many times as specified, resulting in a map of multiple lots and streets. CityEngine can then be instructed to start generating the buildings using defined procedural modeling rules. At this point, the city model can be re-designed and adjusted by changing the parameters or the shape grammar. === Geodesign === Though CityEngine is not an analytical tool like GIS, discussions about geodesign often mention the use of ArcGIS CityEngine. As it can be used to enhance 3D shape generation in ArcGIS, ArcGIS CityEngine is a critical product to improve the applicability of geodesign by using geospatial information to design or analyze a city. == Applications == === Urban design and planning === Garsdale Design used ArcGIS CityEngine in the creation of city master plans in Iraq before 2013, both to model existing historic areas and also model future plans. Larger companies like Foster+Partners and HOK Architects have also used CityEngine in their urban planning projects. === Urban and environmental studies === Because its primary feature is building informative city models, some urban researchers use CityEngine to compare land-use planning schemes, for example in very dense global cities such as Hong Kong and Seoul. Environmental scientists can also utilize the instant 3D model generation in CityEngine, which can make for more convenient informative research than modeling a city by creating each building individually. === Game development === CityEngine can be used as a tool in the creation of video games that require detailed 3D environments to assign interactive scripts. === Movie industry === Zootopia (also known outside of the US as Zootopolis), which won the 2016 Academy Award for Best Animated Feature Film, used CityEngine to model the city in its movie. multi-scaling city, the designers used CityEngine due to its rule-based system. CityEngine was also used to create Big Hero 6's San-Fransokyo. === Military === Due to its integration with the Esri product suite and its ability to process geospatial data to create 3D scenes/maps, CityEngine can be used within military/defense organizations. == List of movies and TV shows using CityEngine == Studios and companies rarely state what software they use in their pipelines. When CityEngine is mentioned as a tool in production, it's often in a small reference in a larger article. Movies only claimed to use CityEngine by a single Esri employee Presented at FMX 2025 workshop == Ports == ArcGIS CityEngine is built on top of Eclipse IDE, and has therefore able to be used on Windows and Linux operating systems. Support for macOS was stopped in March 2021. == Plugins and extensions == ArcGIS CityEngine currently works with a number of third party 3D modeling, rendering, and analytical software products via its SDK and API; these currently are: ArcGIS CityEngine for ArcGIS Urban: ArcGIS Urban Suite Puma: ArcGIS CityEngine for Rhinoceros 3D Palladio: ArcGIS CityEngine for Houdini Serlio: ArcGIS CityEngine for Maya PyPRT: ArcGIS CityEngine for Python ArcGIS CityEngine provides a Python scripting interface built on Jython (current version 2.7.0) which allows users to create their own tools and functionality. == Publications ==

  Read more →
• 

  Relief (feature selection)

  Relief is an algorithm developed by Kenji Kira and Larry Rendell in 1992 that takes a filter-method approach to feature selection that is notably sensitive to feature interactions. It was originally designed for application to binary classification problems with discrete or numerical features. Relief calculates a feature score for each feature which can then be applied to rank and select top scoring features for feature selection. Alternatively, these scores may be applied as feature weights to guide downstream modeling. Relief feature scoring is based on the identification of feature value differences between nearest neighbor instance pairs. If a feature value difference is observed in a neighboring instance pair with the same class (a 'hit'), the feature score decreases. Alternatively, if a feature value difference is observed in a neighboring instance pair with different class values (a 'miss'), the feature score increases. The original Relief algorithm has since inspired a family of Relief-based feature selection algorithms (RBAs), including the ReliefF algorithm. Beyond the original Relief algorithm, RBAs have been adapted to (1) perform more reliably in noisy problems, (2) generalize to multi-class problems (3) generalize to numerical outcome (i.e. regression) problems, and (4) to make them robust to incomplete (i.e. missing) data. To date, the development of RBA variants and extensions has focused on four areas; (1) improving performance of the 'core' Relief algorithm, i.e. examining strategies for neighbor selection and instance weighting, (2) improving scalability of the 'core' Relief algorithm to larger feature spaces through iterative approaches, (3) methods for flexibly adapting Relief to different data types, and (4) improving Relief run efficiency. Their strengths are that they are not dependent on heuristics, they run in low-order polynomial time, and they are noise-tolerant and robust to feature interactions, as well as being applicable for binary or continuous data; however, it does not discriminate between redundant features, and low numbers of training instances fool the algorithm. == Relief Algorithm == Take a data set with n instances of p features, belonging to two known classes. Within the data set, each feature should be scaled to the interval [0 1] (binary data should remain as 0 and 1). The algorithm will be repeated m times. Start with a p-long weight vector (W) of zeros. At each iteration, take the feature vector (X) belonging to one random instance, and the feature vectors of the instance closest to X (by Euclidean distance) from each class. The closest same-class instance is called 'near-hit', and the closest different-class instance is called 'near-miss'. Update the weight vector such that W i = W i − ( x i − n e a r H i t i ) 2 + ( x i − n e a r M i s s i ) 2 , {\displaystyle W_{i}=W_{i}-(x_{i}-\mathrm {nearHit} _{i})^{2}+(x_{i}-\mathrm {nearMiss} _{i})^{2},} where i {\displaystyle i} indexes the components and runs from 1 to p. Thus the weight of any given feature decreases if it differs from that feature in nearby instances of the same class more than nearby instances of the other class, and increases in the reverse case. After m iterations, divide each element of the weight vector by m. This becomes the relevance vector. Features are selected if their relevance is greater than a threshold τ. Kira and Rendell's experiments showed a clear contrast between relevant and irrelevant features, allowing τ to be determined by inspection. However, it can also be determined by Chebyshev's inequality for a given confidence level (α) that a τ of 1/sqrt(αm) is good enough to make the probability of a Type I error less than α, although it is stated that τ can be much smaller than that. Relief was also described as generalizable to multinomial classification by decomposition into a number of binary problems. == ReliefF Algorithm == Kononenko et al. propose a number of updates to Relief. Firstly, they find the near-hit and near-miss instances using the Manhattan (L1) norm rather than the Euclidean (L2) norm, although the rationale is not specified. Furthermore, they found taking the absolute differences between xi and near-hiti, and xi and near-missi to be sufficient when updating the weight vector (rather than the square of those differences). === Reliable probability estimation === Rather than repeating the algorithm m times, implement it exhaustively (i.e. n times, once for each instance) for relatively small n (up to one thousand). Furthermore, rather than finding the single nearest hit and single nearest miss, which may cause redundant and noisy attributes to affect the selection of the nearest neighbors, ReliefF searches for k nearest hits and misses and averages their contribution to the weights of each feature. k can be tuned for any individual problem. === Incomplete data === In ReliefF, the contribution of missing values to the feature weight is determined using the conditional probability that two values should be the same or different, approximated with relative frequencies from the data set. This can be calculated if one or both features are missing. === Multi-class problems === Rather than use Kira and Rendell's proposed decomposition of a multinomial classification into a number of binomial problems, ReliefF searches for k near misses from each different class and averages their contributions for updating W, weighted with the prior probability of each class. == Other Relief-based Algorithm Extensions/Derivatives == The following RBAs are arranged chronologically from oldest to most recent. They include methods for improving (1) the core Relief algorithm concept, (2) iterative approaches for scalability, (3) adaptations to different data types, (4) strategies for computational efficiency, or (5) some combination of these goals. For more on RBAs see these book chapters or this most recent review paper. === RRELIEFF === Robnik-Šikonja and Kononenko propose further updates to ReliefF, making it appropriate for regression. === Relieved-F === Introduced deterministic neighbor selection approach and a new approach for incomplete data handling. === Iterative Relief === Implemented method to address bias against non-monotonic features. Introduced the first iterative Relief approach. For the first time, neighbors were uniquely determined by a radius threshold and instances were weighted by their distance from the target instance. === I-RELIEF === Introduced sigmoidal weighting based on distance from target instance. All instance pairs (not just a defined subset of neighbors) contributed to score updates. Proposed an on-line learning variant of Relief. Extended the iterative Relief concept. Introduced local-learning updates between iterations for improved convergence. === TuRF (a.k.a. Tuned ReliefF) === Specifically sought to address noise in large feature spaces through the recursive elimination of features and the iterative application of ReliefF. === Evaporative Cooling ReliefF === Similarly seeking to address noise in large feature spaces. Utilized an iterative `evaporative' removal of lowest quality features using ReliefF scores in association with mutual information. === EReliefF (a.k.a. Extended ReliefF) === Addressing issues related to incomplete and multi-class data. === VLSReliefF (a.k.a. Very Large Scale ReliefF) === Dramatically improves the efficiency of detecting 2-way feature interactions in very large feature spaces by scoring random feature subsets rather than the entire feature space. === ReliefMSS === Introduced calculation of feature weights relative to average feature 'diff' between instance pairs. === SURF === SURF identifies nearest neighbors (both hits and misses) based on a distance threshold from the target instance defined by the average distance between all pairs of instances in the training data. Results suggest improved power to detect 2-way epistatic interactions over ReliefF. === SURF (a.k.a. SURFStar) === SURF extends the SURF algorithm to not only utilized 'near' neighbors in scoring updates, but 'far' instances as well, but employing inverted scoring updates for 'far instance pairs. Results suggest improved power to detect 2-way epistatic interactions over SURF, but an inability to detect simple main effects (i.e. univariate associations). === SWRF === SWRF extends the SURF algorithm adopting sigmoid weighting to take distance from the threshold into account. Also introduced a modular framework for further developing RBAs called MoRF. === MultiSURF (a.k.a. MultiSURFStar) === MultiSURF extends the SURF algorithm adapting the near/far neighborhood boundaries based on the average and standard deviation of distances from the target instance to all others. MultiSURF uses the standard deviation to define a dead-band zone where 'middle-distance' instances do not contribute to scoring. Evidence suggests MultiSURF performs best in detecting pure 2-way feature interactions. === Reli

  Read more →
• 

  Exploratory blockmodeling

  Exploratory blockmodeling is an (inductive) approach (or a group of approaches) in blockmodeling regarding the specification of an ideal blockmodel. This approach, also known as hypotheses-generating, is the simplest approach, as it "merely involves the definition of the block types permitted as well as of the number of clusters." With this approach, researcher usually defines the best possible blockmodel, which then represent the base for the analysis of the whole network. This approach is usually based on: previous analyses and theoretical considerations, using stricker blockmodel and block types, where the structural equivalence is stricker than the regular equivalence and using smaller number of classes. The opposite approach is called a confirmatory blockmodeling.

  Read more →
• 

  Swish function

  The swish function is a family of mathematical function defined as follows: swish β ⁡ ( x ) = x sigmoid ⁡ ( β x ) = x 1 + e − β x . {\displaystyle \operatorname {swish} _{\beta }(x)=x\operatorname {sigmoid} (\beta x)={\frac {x}{1+e^{-\beta x}}}.} where β {\displaystyle \beta } can be constant (usually set to 1) or trainable and "sigmoid" refers to the logistic function. The swish family was designed to smoothly interpolate between a linear function and the Rectified linear unit (ReLU) function. When considering positive values, Swish is a particular case of doubly parameterized sigmoid shrinkage function defined in . Variants of the swish function include Mish. == Special values == For β = 0, the function is linear: f(x) = x/2. For β = 1, the function is the Sigmoid Linear Unit (SiLU). For β = 1.702, the function approximates GeLU. With β → ∞, the function converges to ReLU. Thus, the swish family smoothly interpolates between a linear function and the ReLU function. Since swish β ⁡ ( x ) = swish 1 ⁡ ( β x ) / β {\displaystyle \operatorname {swish} _{\beta }(x)=\operatorname {swish} _{1}(\beta x)/\beta } , all instances of swish have the same shape as the default swish 1 {\displaystyle \operatorname {swish} _{1}} , zoomed by β {\displaystyle \beta } . One usually sets β > 0 {\displaystyle \beta >0} . When β {\displaystyle \beta } is trainable, this constraint can be enforced by β = e b {\displaystyle \beta =e^{b}} , where b {\displaystyle b} is trainable. swish 1 ⁡ ( x ) = x 2 + x 2 4 − x 4 48 + x 6 480 + O ( x 8 ) {\displaystyle \operatorname {swish} _{1}(x)={\frac {x}{2}}+{\frac {x^{2}}{4}}-{\frac {x^{4}}{48}}+{\frac {x^{6}}{480}}+O\left(x^{8}\right)} swish 1 ⁡ ( x ) = x 2 tanh ⁡ ( x 2 ) + x 2 swish 1 ⁡ ( x ) + swish − 1 ⁡ ( x ) = x tanh ⁡ ( x 2 ) swish 1 ⁡ ( x ) − swish − 1 ⁡ ( x ) = x {\displaystyle {\begin{aligned}\operatorname {swish} _{1}(x)&={\frac {x}{2}}\tanh \left({\frac {x}{2}}\right)+{\frac {x}{2}}\\\operatorname {swish} _{1}(x)+\operatorname {swish} _{-1}(x)&=x\tanh \left({\frac {x}{2}}\right)\\\operatorname {swish} _{1}(x)-\operatorname {swish} _{-1}(x)&=x\end{aligned}}} == Derivatives == Because swish β ⁡ ( x ) = swish 1 ⁡ ( β x ) / β {\displaystyle \operatorname {swish} _{\beta }(x)=\operatorname {swish} _{1}(\beta x)/\beta } , it suffices to calculate its derivatives for the default case. swish 1 ′ ⁡ ( x ) = x + sinh ⁡ ( x ) 4 cosh 2 ⁡ ( x 2 ) + 1 2 {\displaystyle \operatorname {swish} _{1}'(x)={\frac {x+\sinh(x)}{4\cosh ^{2}\left({\frac {x}{2}}\right)}}+{\frac {1}{2}}} so swish 1 ′ ⁡ ( x ) − 1 2 {\displaystyle \operatorname {swish} _{1}'(x)-{\frac {1}{2}}} is odd. swish 1 ″ ⁡ ( x ) = 1 − x 2 tanh ⁡ ( x 2 ) 2 cosh 2 ⁡ ( x 2 ) {\displaystyle \operatorname {swish} _{1}''(x)={\frac {1-{\frac {x}{2}}\tanh \left({\frac {x}{2}}\right)}{2\cosh ^{2}\left({\frac {x}{2}}\right)}}} so swish 1 ″ ⁡ ( x ) {\displaystyle \operatorname {swish} _{1}''(x)} is even. == History == SiLU was first proposed alongside the GELU in 2016, then again proposed in 2017 as the Sigmoid-weighted Linear Unit (SiL) in reinforcement learning. The SiLU/SiL was then again proposed as the SWISH over a year after its initial discovery, originally proposed without the learnable parameter β, so that β implicitly equaled 1. The swish paper was then updated to propose the activation with the learnable parameter β. In 2017, after performing analysis on ImageNet data, researchers from Google indicated that using this function as an activation function in artificial neural networks improves the performance, compared to ReLU and sigmoid functions. It is believed that one reason for the improvement is that the swish function helps alleviate the vanishing gradient problem during backpropagation.

  Read more →
• 

  AdBlock

  AdBlock is an ad-blocking browser extension for Google Chrome, Apple Safari (desktop and mobile), Firefox, Samsung Internet, Microsoft Edge and Opera. AdBlock allows users to prevent page elements, such as advertisements, from being displayed. It is free to download and use, and it includes optional donations to the developers. The AdBlock extension was created on December 8, 2009, which is the day that supports for extensions was added to Google Chrome. It was one of the first Google Chrome extensions that was made. Since 2016, AdBlock has been based on the Adblock Plus source code. In July 2018, AdBlock acquired uBlock, a commercial ad-blocker owned by uBlock LLC and based on uBlock Origin. In April 2021, eyeo GmbH (developer of Adblock Plus) announced its purchase of AdBlock, Inc (formerly BetaFish, Inc). == Crowdfunding == Gundlach launched a crowdfunding campaign on Crowdtilt in August 2013 in order to fund an ad campaign to raise awareness of ad-blocking and to rent a billboard at Times Square. After the one-month campaign, it raised $55,000. == Sales and acceptable ads == AdBlock was sold to an anonymous buyer in 2015 and on October 15, 2015, Gundlach's name was taken down from the site. In the terms of the deal, the original developer Michael Gundlach left operations to Adblock's continuing director, Gabriel Cubbage, and as of October 2, 2015, AdBlock began participating in the Acceptable Ads program. Acceptable Ads identifies "non-annoying" ads, which AdBlock shows by default. The intent is to allow non-invasive advertising, to either maintain support for websites that rely on advertising as a main source of revenue or for websites that have an agreement with the program. == Filters == AdBlock uses EasyList, the same filter syntax as Adblock Plus for Firefox, and natively supports the use of a number of filter lists. == Partnership with Amnesty International == On March 12, 2016, in support of World Day Against Cyber Censorship, and in partnership with Amnesty International, instead of blocking ads, AdBlock replaced ads with banners linked to articles on Amnesty's website, written by prominent free speech advocates such as Edward Snowden, to raise awareness of government-imposed online censorship and digital privacy issues around the world. The campaign was met with both praise and criticism, with AdBlock's CEO, Gabriel Cubbage, defending the decision in an essay on AdBlock's website, saying "We’re showing you Amnesty banners, just for today, because we believe users should be part of the conversation about online privacy. Tomorrow, those spaces will be vacant again. But take a moment to consider that in an increasingly information-driven world, when your right to digital privacy is threatened, so is your right to free expression." Meanwhile, Simon Sharwood of The Register characterized Cubbage's position as "'You should control your computer except when we feel political', says AdBlock CEO". == AdBlock for Firefox == On September 13, 2014, the AdBlock team released a version for Firefox users, ported from the code for Google Chrome, released under the same free software license as the original Adblock. The extension was removed on April 2, 2015, by an administrator on Mozilla Add-ons. On December 7, 2015, the official AdBlock site's knowledge base article stated that with version 44 or higher of Firefox desktop and Firefox Mobile, AdBlock will not be supported. The last version of Adblock for those platforms will work on older versions of Firefox. AdBlock was released again on Mozilla Add-ons on November 17, 2016. On April 1, 2012, Adblock developer Michael Gundlach tweaked the code to display LOLcats instead of simply blocking ads. Initially developed as a short-lived April Fools joke, the response was so positive that CatBlock was continued to be offered as an optional add-on supported by a monthly subscription. On October 23, 2014, the developer decided to end official support for CatBlock, and made it open-source, under GPLv3 licensing, as the original extension.

  Read more →
• 

  Information gain (decision tree)

  In the context of decision trees in information theory and machine learning, information gain refers to the conditional expected value of the Kullback–Leibler divergence of the univariate probability distribution of one variable from the conditional distribution of this variable given the other one. (In broader contexts, information gain can also be used as a synonym for either Kullback–Leibler divergence or mutual information, but the focus of this article is on the more narrow meaning below.) Explicitly, the information gain of a random variable X {\displaystyle X} obtained from an observation of a random variable A {\displaystyle A} taking value a {\displaystyle a} is defined as: I G ( X , a ) = D KL ( P X ∣ a ∥ P X ) {\displaystyle {\mathit {IG}}(X,a)=D_{\text{KL}}{\bigl (}P_{X\mid a}\parallel P_{X}{\bigr )}} In other words, it is the Kullback–Leibler divergence of P X ( x ) {\displaystyle P_{X}(x)} (the prior distribution for X {\displaystyle X} ) from P X ∣ a ( x ) {\displaystyle P_{X\mid a}(x)} (the posterior distribution for X {\displaystyle X} given A = a {\displaystyle A=a} ). The expected value of the information gain is the mutual information I ( X ; A ) {\displaystyle I(X;A)} : E A ⁡ [ I G ( X , A ) ] = I ( X ; A ) {\displaystyle \operatorname {E} _{A}[{\mathit {IG}}(X,A)]=I(X;A)} i.e. the reduction in the entropy of X {\displaystyle X} achieved by learning the state of the random variable A {\displaystyle A} . In machine learning, this concept can be used to define a preferred sequence of attributes to investigate to most rapidly narrow down the state of X. Such a sequence (which depends on the outcome of the investigation of previous attributes at each stage) is called a decision tree, and when applied in the area of machine learning is known as decision tree learning. Usually an attribute with high mutual information should be preferred to other attributes. == General definition == In general terms, the expected information gain is the reduction in information entropy Η from a prior state to a state that takes some information as given: I G ( T , a ) = H ( T ) − H ( T | a ) , {\displaystyle IG(T,a)=\mathrm {H} {(T)}-\mathrm {H} {(T|a)},} where H ( T | a ) {\displaystyle \mathrm {H} {(T|a)}} is the conditional entropy of T {\displaystyle T} given the value of attribute a {\displaystyle a} . This is intuitively plausible when interpreting entropy Η as a measure of uncertainty of a random variable T {\displaystyle T} : by learning (or assuming) a {\displaystyle a} about T {\displaystyle T} , our uncertainty about T {\displaystyle T} is reduced (i.e. I G ( T , a ) {\displaystyle IG(T,a)} is positive), unless of course T {\displaystyle T} is independent of a {\displaystyle a} , in which case H ( T | a ) = H ( T ) {\displaystyle \mathrm {H} (T|a)=\mathrm {H} (T)} , meaning I G ( T , a ) = 0 {\displaystyle IG(T,a)=0} . == Formal definition == Let T denote a set of training examples, each of the form ( x , y ) = ( x 1 , x 2 , x 3 , . . . , x k , y ) {\displaystyle ({\textbf {x}},y)=(x_{1},x_{2},x_{3},...,x_{k},y)} where x a ∈ v a l s ( a ) {\displaystyle x_{a}\in \mathrm {vals} (a)} is the value of the a th {\displaystyle a^{\text{th}}} attribute or feature of example x {\displaystyle {\textbf {x}}} and y is the corresponding class label. The information gain for an attribute a is defined in terms of Shannon entropy H ( − ) {\displaystyle \mathrm {H} (-)} as follows. For a value v taken by attribute a, let S a ( v ) = { x ∈ T | x a = v } {\displaystyle S_{a}{(v)}=\{{\textbf {x}}\in T|x_{a}=v\}} be defined as the set of training inputs of T for which attribute a is equal to v. Then the information gain of T for attribute a is the difference between the a priori Shannon entropy H ( T ) {\displaystyle \mathrm {H} (T)} of the training set and the conditional entropy H ( T | a ) {\displaystyle \mathrm {H} {(T|a)}} . H ( T | a ) = ∑ v ∈ v a l s ( a ) | S a ( v ) | | T | ⋅ H ( S a ( v ) ) . {\displaystyle \mathrm {H} (T|a)=\sum _{v\in \mathrm {vals} (a)}{{\frac {|S_{a}{(v)}|}{|T|}}\cdot \mathrm {H} \left(S_{a}{\left(v\right)}\right)}.} I G ( T , a ) = H ( T ) − H ( T | a ) {\displaystyle IG(T,a)=\mathrm {H} (T)-\mathrm {H} (T|a)} The mutual information is equal to the total entropy for an attribute if for each of the attribute values a unique classification can be made for the result attribute. In this case, the relative entropies subtracted from the total entropy are 0. In particular, the values v ∈ v a l s ( a ) {\displaystyle v\in vals(a)} defines a partition of the training set data T into mutually exclusive and all-inclusive subsets, inducing a categorical probability distribution P a ( v ) {\textstyle P_{a}{(v)}} on the values v ∈ v a l s ( a ) {\textstyle v\in vals(a)} of attribute a. The distribution is given P a ( v ) := | S a ( v ) | | T | {\textstyle P_{a}{(v)}:={\frac {|S_{a}{(v)}|}{|T|}}} . In this representation, the information gain of T given a can be defined as the difference between the unconditional Shannon entropy of T and the expected entropy of T conditioned on a, where the expectation value is taken with respect to the induced distribution on the values of a. I G ( T , a ) = H ( T ) − ∑ v ∈ v a l s ( a ) P a ( v ) H ( S a ( v ) ) = H ( T ) − E P a [ H ( S a ( v ) ) ] = H ( T ) − H ( T | a ) . {\displaystyle {\begin{alignedat}{2}IG(T,a)&=\mathrm {H} (T)-\sum _{v\in \mathrm {vals} (a)}{P_{a}{(v)}\mathrm {H} \left(S_{a}{(v)}\right)}\\&=\mathrm {H} (T)-\mathbb {E} _{P_{a}}{\left[\mathrm {H} {(S_{a}{(v)})}\right]}\\&=\mathrm {H} (T)-\mathrm {H} {(T|a)}.\end{alignedat}}} == Example == In engineering applications, information is analogous to signal, and entropy is analogous to noise. It determines how a decision tree chooses to split data. The leftmost figure below is very impure and has high entropy corresponding to higher disorder and lower information value. As we go to the right, the entropy decreases, and the information value increases. Now, it is clear that information gain is the measure of how much information a feature provides about a class. Let's visualize information gain in a decision tree as shown in the right: The node t is the parent node, and the sub-nodes tL and tR are child nodes. In this case, the parent node t has a collection of cancer and non-cancer samples denoted as C and NC respectively. We can use information gain to determine how good the splitting of nodes is in a decision tree. In terms of entropy, information gain is defined as: To understand this idea, let's start by an example in which we create a simple dataset and want to see if gene mutations could be related to patients with cancer. Given four different gene mutations, as well as seven samples, the training set for a decision can be created as follows: In this dataset, a 1 means the sample has the mutation (True), while a 0 means the sample does not (False). A sample with C denotes that it has been confirmed to be cancerous, while NC means it is non-cancerous. Using this data, a decision tree can be created with information gain used to determine the candidate splits for each node. For the next step, the entropy at parent node t of the above simple decision tree is computed as:H(t) = −[pC,t log2(pC,t) + pNC,t log2(pNC,t)] where, probability of selecting a class ‘C’ sample at node t, pC,t = n(t, C) / n(t), probability of selecting a class ‘NC’ sample at node t, pNC,t = n(t, NC) / n(t), n(t), n(t, C), and n(t, NC) are the number of total samples, ‘C’ samples and ‘NC’ samples at node t respectively.Using this with the example training set, the process for finding information gain beginning with H ( t ) {\displaystyle \mathrm {H} {(t)}} for Mutation 1 is as follows: pC, t = 4/7 pNC, t = 3/7 H ( t ) {\displaystyle \mathrm {H} {(t)}} = −(4/7 × log2(4/7) + 3/7 × log2(3/7)) = 0.985 Note: H ( t ) {\displaystyle \mathrm {H} {(t)}} will be the same for all mutations at the root. The relatively high value of entropy H ( t ) = 0.985 {\displaystyle \mathrm {H} {(t)}=0.985} (1 is the optimal value) suggests that the root node is highly impure and the constituents of the input at the root node would look like the leftmost figure in the above Entropy Diagram. However, such a set of data is good for learning the attributes of the mutations used to split the node. At a certain node, when the homogeneity of the constituents of the input occurs (as shown in the rightmost figure in the above Entropy Diagram), the dataset would no longer be good for learning. Moving on, the entropy at left and right child nodes of the above decision tree is computed using the formulae:H(tL) = −[pC,L log2(pC,L) + pNC,L log2(pNC,L)]H(tR) = −[pC,R log2(pC,R) + pNC,R log2(pNC,R)]where, probability of selecting a class ‘C’ sample at the left child node, pC,L = n(tL, C) / n(tL), probability of selecting a class ‘NC’ sample at the left child node, pNC,L = n(tL, NC) / n(tL), probability of selecting a class ‘C’ sample at the right child node, pC,R = n(tR, C) / n(tR), prob

  Read more →
• 

  Gaussian adaptation

  Gaussian adaptation (GA), also called normal or natural adaptation (NA) is an evolutionary algorithm designed for the maximization of manufacturing yield due to statistical deviation of component values of signal processing systems. In short, GA is a stochastic adaptive process where a number of samples of an n-dimensional vector x[xT = (x1, x2, ..., xn)] are taken from a multivariate Gaussian distribution, N(m, M), having mean m and moment matrix M. The samples are tested for fail or pass. The first- and second-order moments of the Gaussian restricted to the pass samples are m and M. The outcome of x as a pass sample is determined by a function s(x), 0 < s(x) < q ≤ 1, such that s(x) is the probability that x will be selected as a pass sample. The average probability of finding pass samples (yield) is P ( m ) = ∫ s ( x ) N ( x − m ) d x {\displaystyle P(m)=\int s(x)N(x-m)\,dx} Then the theorem of GA states: For any s(x) and for any value of P < q, there always exist a Gaussian p. d. f. [ probability density function ] that is adapted for maximum dispersion. The necessary conditions for a local optimum are m = m and M proportional to M. The dual problem is also solved: P is maximized while keeping the dispersion constant (Kjellström, 1991). Proofs of the theorem may be found in the papers by Kjellström, 1970, and Kjellström & Taxén, 1981. Since dispersion is defined as the exponential of entropy/disorder/average information it immediately follows that the theorem is valid also for those concepts. Altogether, this means that Gaussian adaptation may carry out a simultaneous maximisation of yield and average information (without any need for the yield or the average information to be defined as criterion functions). The theorem is valid for all regions of acceptability and all Gaussian distributions. It may be used by cyclic repetition of random variation and selection (like the natural evolution). In every cycle a sufficiently large number of Gaussian distributed points are sampled and tested for membership in the region of acceptability. The centre of gravity of the Gaussian, m, is then moved to the centre of gravity of the approved (selected) points, m. Thus, the process converges to a state of equilibrium fulfilling the theorem. A solution is always approximate because the centre of gravity is always determined for a limited number of points. It was used for the first time in 1969 as a pure optimization algorithm making the regions of acceptability smaller and smaller (in analogy to simulated annealing, Kirkpatrick 1983). Since 1970 it has been used for both ordinary optimization and yield maximization. == Natural evolution and Gaussian adaptation == It has also been compared to the natural evolution of populations of living organisms. In this case s(x) is the probability that the individual having an array x of phenotypes will survive by giving offspring to the next generation; a definition of individual fitness given by Hartl 1981. The yield, P, is replaced by the mean fitness determined as a mean over the set of individuals in a large population. Phenotypes are often Gaussian distributed in a large population and a necessary condition for the natural evolution to be able to fulfill the theorem of Gaussian adaptation, with respect to all Gaussian quantitative characters, is that it may push the centre of gravity of the Gaussian to the centre of gravity of the selected individuals. This may be accomplished by the Hardy–Weinberg law. This is possible because the theorem of Gaussian adaptation is valid for any region of acceptability independent of the structure (Kjellström, 1996). In this case the rules of genetic variation such as crossover, inversion, transposition etcetera may be seen as random number generators for the phenotypes. So, in this sense Gaussian adaptation may be seen as a genetic algorithm. == How to climb a mountain == Mean fitness may be calculated provided that the distribution of parameters and the structure of the landscape is known. The real landscape is not known, but figure below shows a fictitious profile (blue) of a landscape along a line (x) in a room spanned by such parameters. The red curve is the mean based on the red bell curve at the bottom of figure. It is obtained by letting the bell curve slide along the x-axis, calculating the mean at every location. As can be seen, small peaks and pits are smoothed out. Thus, if evolution is started at A with a relatively small variance (the red bell curve), then climbing will take place on the red curve. The process may get stuck for millions of years at B or C, as long as the hollows to the right of these points remain, and the mutation rate is too small. If the mutation rate is sufficiently high, the disorder or variance may increase and the parameter(s) may become distributed like the green bell curve. Then the climbing will take place on the green curve, which is even more smoothed out. Because the hollows to the right of B and C have now disappeared, the process may continue up to the peaks at D. But of course the landscape puts a limit on the disorder or variability. Besides — dependent on the landscape — the process may become very jerky, and if the ratio between the time spent by the process at a local peak and the time of transition to the next peak is very high, it may as well look like a punctuated equilibrium as suggested by Gould (see Ridley). == Computer simulation of Gaussian adaptation == Thus far the theory only considers mean values of continuous distributions corresponding to an infinite number of individuals. In reality however, the number of individuals is always limited, which gives rise to an uncertainty in the estimation of m and M (the moment matrix of the Gaussian). And this may also affect the efficiency of the process. Unfortunately very little is known about this, at least theoretically. The implementation of normal adaptation on a computer is a fairly simple task. The adaptation of m may be done by one sample (individual) at a time, for example m(i + 1) = (1 – a) m(i) + ax where x is a pass sample, and a < 1 a suitable constant so that the inverse of a represents the number of individuals in the population. M may in principle be updated after every step y leading to a feasible point x = m + y according to: M(i + 1) = (1 – 2b) M(i) + 2byyT, where yT is the transpose of y and b << 1 is another suitable constant. In order to guarantee a suitable increase of average information, y should be normally distributed with moment matrix μ2M, where the scalar μ > 1 is used to increase average information (information entropy, disorder, diversity) at a suitable rate. But M will never be used in the calculations. Instead we use the matrix W defined by WWT = M. Thus, we have y = Wg, where g is normally distributed with the moment matrix μU, and U is the unit matrix. W and WT may be updated by the formulas W = (1 – b)W + bygT and WT = (1 – b)WT + bgyT because multiplication gives M = (1 – 2b)M + 2byyT, where terms including b2 have been neglected. Thus, M will be indirectly adapted with good approximation. In practice it will suffice to update W only W(i + 1) = (1 – b)W(i) + bygT. This is the formula used in a simple 2-dimensional model of a brain satisfying the Hebbian rule of associative learning; see the next section (Kjellström, 1996 and 1999). The figure below illustrates the effect of increased average information in a Gaussian p.d.f. used to climb a mountain Crest (the two lines represent the contour line). Both the red and green cluster have equal mean fitness, about 65%, but the green cluster has a much higher average information making the green process much more efficient. The effect of this adaptation is not very salient in a 2-dimensional case, but in a high-dimensional case, the efficiency of the search process may be increased by many orders of magnitude. == The evolution in the brain == In the brain the evolution of DNA-messages is supposed to be replaced by an evolution of signal patterns and the phenotypic landscape is replaced by a mental landscape, the complexity of which will hardly be second to the former. The metaphor with the mental landscape is based on the assumption that certain signal patterns give rise to a better well-being or performance. For instance, the control of a group of muscles leads to a better pronunciation of a word or performance of a piece of music. In this simple model it is assumed that the brain consists of interconnected components that may add, multiply and delay signal values. A nerve cell kernel may add signal values, a synapse may multiply with a constant and An axon may delay values. This is a basis of the theory of digital filters and neural networks consisting of components that may add, multiply and delay signalvalues and also of many brain models, Levine 1991. In the figure below the brain stem is supposed to deliver Gaussian distributed signal patterns. This may be possible since certai

  Read more →
• 

  State–action–reward–state–action

  State–action–reward–state–action (SARSA) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. It was proposed by Rummery and Niranjan in a technical note with the name "Modified Connectionist Q-Learning" (MCQ-L). The alternative name SARSA, proposed by Rich Sutton, was only mentioned as a footnote. This name reflects the fact that the main function for updating the Q-value depends on the current state of the agent "S1", the action the agent chooses "A1", the reward "R2" the agent gets for choosing this action, the state "S2" that the agent enters after taking that action, and finally the next action "A2" the agent chooses in its new state. The acronym for the quintuple (St, At, Rt+1, St+1, At+1) is SARSA. Some authors use a slightly different convention and write the quintuple (St, At, Rt, St+1, At+1), depending on which time step the reward is formally assigned. The rest of the article uses the former convention. == Algorithm == Q new ( S t , A t ) ← ( 1 − α ) Q ( S t , A t ) + α [ R t + 1 + γ Q ( S t + 1 , A t + 1 ) ] {\displaystyle Q^{\textrm {new}}(S_{t},A_{t})\leftarrow (1-\alpha )Q(S_{t},A_{t})+\alpha \,[R_{t+1}+\gamma \,Q(S_{t+1},A_{t+1})]} A SARSA agent interacts with the environment and updates the policy based on actions taken, hence this is known as an on-policy learning algorithm. The Q value for a state-action is updated by an error, adjusted by the learning rate α. Q values represent the possible reward received in the next time step for taking action a in state s, plus the discounted future reward received from the next state-action observation. Watkin's Q-learning updates an estimate of the optimal state-action value function Q ∗ {\displaystyle Q^{}} based on the maximum reward of available actions. While SARSA learns the Q values associated with taking the policy it follows itself, Watkin's Q-learning learns the Q values associated with taking the optimal policy while following an exploration/exploitation policy. Some optimizations of Watkin's Q-learning may be applied to SARSA. == Hyperparameters == === Learning rate (alpha) === The learning rate determines to what extent newly acquired information overrides old information. A factor of 0 will make the agent not learn anything, while a factor of 1 would make the agent consider only the most recent information. === Discount factor (gamma) === The discount factor determines the importance of future rewards. A discount factor of 0 makes the agent "opportunistic", or "myopic", e.g., by only considering current rewards, while a factor approaching 1 will make it strive for a long-term high reward. If the discount factor meets or exceeds 1, the Q {\displaystyle Q} values may diverge. === Initial conditions (Q(S0, A0)) === Since SARSA is an iterative algorithm, it implicitly assumes an initial condition before the first update occurs. A high (infinite) initial value, also known as "optimistic initial conditions", can encourage exploration: no matter what action takes place, the update rule causes it to have higher values than the other alternative, thus increasing their choice probability. In 2013 it was suggested that the first reward r {\displaystyle r} could be used to reset the initial conditions. According to this idea, the first time an action is taken the reward is used to set the value of Q {\displaystyle Q} . This allows immediate learning in case of fixed deterministic rewards. This resetting-of-initial-conditions (RIC) approach seems to be consistent with human behavior in repeated binary choice experiments.

  Read more →
• 

  Josh (app)

  Josh (stylized as JOSH) was a video-sharing social networking service but it has since evolved into a live call and chat application owned by VerSe Innovation – an Indian technology company based in Bangalore, India. Josh was an Indian short video app that was launched in immediately after the Indian Government banned TikTok and other Chinese apps in June 2020. The founders of the platform have promoted the app as the “Instagram for Bharat” referring to their focus on the Indian audience that speaks its own regional and state languages. Josh was among the top 10 most downloaded apps social and entertainment apps in India of 2021 and had 150 million monthly active users as per April 2022. The word 'Josh' translates to fervour or passion. The app was launched under the aegis of the Atmanirbhar Bharat campaign and to compete with the duopoly of Google and Facebook in India. Josh's parent company VerSe Innovations Pvt. Ltd. owns another startup Dailyhunt, which a content and news aggregator application. Both Dailyhunt and Josh are a part of the VerSe's focus on the "next billion" regional language users of India. Founders Virendra Gupta and Umang Bedi conceptualised Josh as a short-video platform that made content creation accessible to vernacular language users, essentially the non-English speaking audience in India. == Features == Josh is currently available in 12 Indian languages and allows users to upload, share, remix bite-sized videos of up to 120 seconds. There are various categories across the video section including viral, trending, glamour, dance, devotion, yoga and cooking among others. Similar to Instagram and TikTok, it has a video feed which is curated for individuals on the basis of their app behaviour. The app hosts many daily, weekly and monthly social media challenges. == Funding == In December 2020, within 3 months of its launch, Josh's parent app VerSe Innovation raised more than $100 million from investors including Alphabet Inc's Google and Microsoft. In February 2021, VerSe Innovation raised $100 million in Series H funding from Qatar Investment Authority, the sovereign wealth fund of the State of Qatar, and Glade Brook Capital Partners. In August 2021, VerSe raised over $450 million in its Series I financing round with a valuation of $1 billion. Investors included Canada Pension Plan Investment Board (CPPIB), Siguler Guff, Baillie Gifford, Carlyle Asia Partners Growth II affiliates, and others. The startup announced its plan to expand overseas and broaden its ecommerce play for both Dailyhunt and Josh. In April 2022, VerSe announced that it has raised $805 million in funding from investors at a valuation of nearly $5 billion. ByteDance Offloads Stake In Josh Parent VerSe, Exits At 56% Discount == Partnerships == In February 2021, Saregama and Josh signed a music licensing deal, wherein Josh expanded its musical library with 1.3 lakh songs from Saregama in 25 different languages. To improve their user experience, Josh partnered with computer vision company D-ID in August 2021. The company helped Josh introduce photo-to-video features, live portrait technology, animate their photos etc. In order to solidify their efforts in enhancing Josh, VerSe acquired Indian social networking platform GolBol in October 2021. The move came as an effort by the startup to strengthen their discovery initiatives on the platform and classify content at scale and understand the core behaviour of Indian regional audiences. Josh has also announced its plans to include live commerce as a potential revenue stream through its partnership with multiple large e-commerce players. == Notable campaigns == Say No To Dowry – In association with Josh, the Kerala Police partook in the #SayNo2Dowry online social media campaign that was started to highlight and stop the social evil in the state. Salute India – Josh entered the Guinness World Records by creating the largest online video album of people saluting (29,529). It organised an online campaign #SaluteIndia on the app during the 75th Independence Day of India during 10–15 August 2021.

  Read more →
• 

  Types of artificial neural networks

  Types of neural networks (NN) include a family of techniques. The simplest types have static components, including number of units, number of layers, unit weights and topology. Dynamic NNs evolve via learning. Some types allow/require learning to be "supervised" by the operator, while others operate independently. Some types operate purely in hardware, while others are purely software and run on general purpose computers. The main types are: Transformers: these use attention to analyze every token in the input stream against every other token in the stream. That technique has enabled neural networks to reach the general public via chatbots, code generators and many other forms. Convolutional neural networks (CNN): a FNN that uses kernels and regularization to evade problems in prior generations of NNs. They are typically used to analyze visual and other two-dimensional data. Generative adversarial networks set networks (of varying structure) against each other, each trying to push the other(s) to produce better results such as winning a game or to deceive the opponent about the authenticity of an input. == Feedforward == In feedforward neural networks the information moves from the input to output directly in every layer. There can be hidden layers with or without cycles/loops to sequence inputs. Feedforward networks can be constructed with various types of units, such as binary McCulloch–Pitts neurons, the simplest of which is the perceptron. Continuous neurons, frequently with sigmoidal activation, are used in the context of backpropagation. == Group method of data handling == The Group Method of Data Handling (GMDH) features fully automatic structural and parametric model optimization. The node activation functions are Kolmogorov–Gabor polynomials that permit additions and multiplications. It uses a deep multilayer perceptron with eight layers. It is a supervised learning network that grows layer by layer, where each layer is trained by regression analysis. Useless items are detected using a validation set, and pruned through regularization. The size and depth of the resulting network depends on the task. == Autoencoder == An autoencoder, autoassociator or Diabolo network is similar to the multilayer perceptron (MLP) – with an input layer, an output layer and one or more hidden layers connecting them. However, the output layer has the same number of units as the input layer. Its purpose is to reconstruct its own inputs (instead of emitting a target value). Therefore, autoencoders are unsupervised learning models. An autoencoder is used for unsupervised learning of efficient codings, typically for the purpose of dimensionality reduction and for learning generative models of data. == Probabilistic == A probabilistic neural network (PNN) is a four-layer feedforward neural network. The layers are Input, hidden pattern, hidden summation, and output. In the PNN algorithm, the parent probability distribution function (PDF) of each class is approximated by a Parzen window and a non-parametric function. Then, using PDF of each class, the class probability of a new input is estimated and Bayes’ rule is employed to allocate it to the class with the highest posterior probability. It was derived from the Bayesian network and a statistical algorithm called Kernel Fisher discriminant analysis. It is used for classification and pattern recognition. == Time delay == A time delay neural network (TDNN) is a feedforward architecture for sequential data that recognizes features independent of sequence position. In order to achieve time-shift invariance, delays are added to the input so that multiple data points (points in time) are analyzed together. It usually forms part of a larger pattern recognition system. It has been implemented using a perceptron network whose connection weights were trained with back propagation (supervised learning). == Convolutional == A convolutional neural network (CNN, or ConvNet or shift invariant or space invariant) is a class of deep network, composed of one or more convolutional layers with fully connected layers (matching those in typical ANNs) on top. It uses tied weights and pooling layers. In particular, max-pooling. It is often structured via Fukushima's convolutional architecture. They are variations of multilayer perceptrons that use minimal preprocessing. This architecture allows CNNs to take advantage of the 2D structure of input data. Its unit connectivity pattern is inspired by the organization of the visual cortex. Units respond to stimuli in a restricted region of space known as the receptive field. Receptive fields partially overlap, over-covering the entire visual field. Unit response can be approximated mathematically by a convolution operation. CNNs are suitable for processing visual and other two-dimensional data. They have shown superior results in both image and speech applications. They can be trained with standard backpropagation. CNNs are easier to train than other regular, deep, feed-forward neural networks and have many fewer parameters to estimate. Capsule Neural Networks (CapsNet) add structures called capsules to a CNN and reuse output from several capsules to form more stable (with respect to various perturbations) representations. Examples of applications in computer vision include DeepDream and robot navigation. They have wide applications in image and video recognition, recommender systems and natural language processing. == Deep stacking network == A deep stacking network (DSN) (deep convex network) is based on a hierarchy of blocks of simplified neural network modules. It was introduced in 2011 by Deng and Yu. It formulates the learning as a convex optimization problem with a closed-form solution, emphasizing the mechanism's similarity to stacked generalization. Each DSN block is a simple module that is easy to train by itself in a supervised fashion without backpropagation for the entire blocks. Each block consists of a simplified multi-layer perceptron (MLP) with a single hidden layer. The hidden layer h has logistic sigmoidal units, and the output layer has linear units. Connections between these layers are represented by weight matrix U; input-to-hidden-layer connections have weight matrix W. Target vectors t form the columns of matrix T, and the input data vectors x form the columns of matrix X. The matrix of hidden units is H = σ ( W T X ) {\displaystyle {\boldsymbol {H}}=\sigma ({\boldsymbol {W}}^{T}{\boldsymbol {X}})} . Modules are trained in order, so lower-layer weights W are known at each stage. The function performs the element-wise logistic sigmoid operation. Each block estimates the same final label class y, and its estimate is concatenated with original input X to form the expanded input for the next block. Thus, the input to the first block contains the original data only, while downstream blocks' input adds the output of preceding blocks. Then learning the upper-layer weight matrix U given other weights in the network can be formulated as a convex optimization problem: min U T f = ‖ U T H − T ‖ F 2 , {\displaystyle \min _{U^{T}}f=\|{\boldsymbol {U}}^{T}{\boldsymbol {H}}-{\boldsymbol {T}}\|_{F}^{2},} which has a closed-form solution. Unlike other deep architectures, such as DBNs, the goal is not to discover the transformed feature representation. The structure of the hierarchy of this kind of architecture makes parallel learning straightforward, as a batch-mode optimization problem. In purely discriminative tasks, DSNs outperform conventional DBNs. === Tensor deep stacking networks === This architecture is a DSN extension. It offers two important improvements: it uses higher-order information from covariance statistics, and it transforms the non-convex problem of a lower-layer to a convex sub-problem of an upper-layer. TDSNs use covariance statistics in a bilinear mapping from each of two distinct sets of hidden units in the same layer to predictions, via a third-order tensor. While parallelization and scalability are not considered seriously in conventional DNNs, all learning for DSNs and TDSNs is done in batch mode, to allow parallelization. Parallelization allows scaling the design to larger (deeper) architectures and data sets. The basic architecture is suitable for diverse tasks such as classification and regression. == Physics-informed == Such a neural network is designed for the numerical solution of mathematical equations, such as differential, integral, delay, fractional and others. As input parameters, PINN accepts variables (spatial, temporal, and others), transmits them through the network block. At the output, it produces an approximate solution and substitutes it into the mathematical model, considering the initial and boundary conditions. If the solution does not satisfy the required accuracy, one uses the backpropagation and rectify the solution. Besides PINN, other architectures have been developed to produce surrogate models for scientific comput

  Read more →
• 

  European Conference on Computer Vision

  The European Conference on Computer Vision (ECCV) is a biennial research conference with the proceedings published by Springer Science+Business Media. Similar to ICCV in scope and quality, it is held those years which ICCV is not. It is considered to be one of the top conferences in computer vision, alongside CVPR and ICCV, with an 'A' rating from the Australian Ranking of ICT Conferences and an 'A1' rating from the Brazilian ministry of education. The acceptance rate for ECCV 2010 was 24.4% for posters and 3.3% for oral presentations. Like other top computer vision conferences, ECCV has tutorial talks, technical sessions, and poster sessions. The conference is usually spread over five to six days with the main technical program occupying three days in the middle, and tutorial and workshops, focused on specific topics, being held in the beginning and at the end. The ECCV presents the Koenderink Prize annually to recognize fundamental contributions in computer vision. == Location == The conference is usually held in autumn in Europe.

  Read more →