AI Art Keywords

AI Art Keywords — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Digital Image Processing with Sound

  DIPS (Digital Image Processing with Sound) is a set of plug-in objects that handle real-time digital image processing in Max/MSP programming environment. Combining with the built-in objects of the environment, DIPS enables to program the interaction between audio and visual events with ease, and supports the realization of interactive multimedia art as well as interactive computer music. == Summary of Features == A plug-in software for Max/MSP (Max 5 and 6) More than 300 Max external objects and abstractions More than 90 OpenGL objects included More than 110 visual effect objects (Dfx library, Core Image Filters) A utility library for the easy of programming (prefix Dlib) A comprehensive set of sample patches, and a detailed tutorial Handling images & movie files (QuickTime, OpenGL) Render and move 3D models (OpenGL) Video signal input (QuickTime, video texture) Video input analysis: motion detect, face tracking (OpenCV, OpenGL) Importing 3D models (.obj file) Importing Quartz Composer files OpenGL Shading Language (GLSL) programming interface Easy integration of visual events using DIPSWindowMixer (OpenGL) == Description == DIPS is a free plug-in software (a set of external objects) for Max/MSP. It supports the designing of the interaction between sound and visual events in Max using Apple’s Core Image, OpenGL and OpenCV technologies, and consequently, provides a powerful and user-friendly programming environment for the creation of interactive multimedia art. DIPS can be used to detect a performer’s motions and to track positions of subtle details, such as the face, mouth, and eyes. It can also be used to measure the distance between objects and a Kinect sensor system, and offers powerful tools for realtime image processing of incoming video stream and stored movie files. In addition, it can be used to create complex images in a virtual three-dimensional space. The DIPS consists of a library of more than 300 Max external objects and abstractions, a comprehensive set of sample patches, and a detailed tutorial. Some of its strong points, in comparison with other similar plug-ins and software, are its ease of programming, power, and efficiency. The sample patches and tutorial contained in the installation package allows composers and artists who are interested in the creation of interactive art to realize sophisticated realtime video effects on a live video signal at their first practice. And because of its ease of programming, it is likely that one will soon acquire skills needed to create state-of-the-art interactive performance works, multimedia installations, interactive multimedia artworks, and Max VJ applications using DIPS. == History == Initially developed by Shu Matsuda in 1997, DIPS was a plug-in software for Max/FTS running on SGI Octane and O2 computers. Since 2000, it has been developed by the DIPS Development Group supervised by Takayuki Rai. Current active group members are Shu Matsuda, Yota Morimoto, Takuto Fukuda, and Keitaro Takahashi. Previously, Chikashi Miyama, Daichi Ando and Takayuki Hamano also contributed to its development. 2013 DIPS5 for Max (Mac OS X) 2009 DIPS4 for Max/MSP (Mac OS X) 2006 DIPS3 for Max/MSP (Mac OS X) 2003 DIPS2 for jMax4 (Mac OS X) 2002 DIPS for jMax2 (Mac OS X & Linux) 2000 DIPS for jMax (Linux)

  Read more →
• 

  Personality computing

  Personality computing is a research field related to artificial intelligence and personality psychology that studies personality by means of computational techniques from different sources, including text, multimedia, and social networks. == Overview == Personality computing addresses three main problems involving personality: automatic personality recognition, perception, and synthesis. Automatic personality recognition is the inference of the personality type of target individuals from their digital footprint. Automatic personality perception is the inference of the personality attributed by an observer to a target individual based on some observable behavior. Automatic personality synthesis is the generation of the style or behaviour of artificial personalities in Avatars and virtual agents. Self-assessed personality tests or observer ratings are always exploited as the ground truth for testing and validating the performance of artificial intelligence algorithms for the automatic prediction of personality types. There is a wide variety of personality tests, such as the Myers Briggs Type Indicator (MBTI) or the MMPI, but the most used are tests based on the Five Factor Model such as the Revised NEO Personality Inventory. Personality computing can be considered as an extension or complement of Affective computing, where the former focuses on personality traits and the latter on affective states. A further extension of the two fields is Character Computing which combines various character states and traits including but not limited to personality and affect. == History == Personality computing began around 2005 with the pioneering research in personality recognition by Shlomo Argamon and later by François Mairesse. These works showed that personality traits could be inferred with reasonable accuracy from text, such as blogs, self-presentations, and email addresses. In 2008, the concept of "portable personality" for the distributed management of personality profiles has been developed. A few years later, research began in personality recognition and perception from multimodal and social signals, such as recorded meetings and voice calls. In the 2010s, the research focused mainly on personality recognition and perception from social media, helped by the first workshops organized by Fabio Celli. In particular personality was extracted from Facebook, Twitter and Instagram. In the same years, automatic personality synthesis helped improve the coherence of simulated behavior in virtual agents. Scientific works by Michal Kosinski demonstrated the validity of Personality Computing from different digital footprints, in particular from user preferences such as Facebook page likes, showed that machines can recognize personality better than humans and raised a warning against Cambridge Analytica and misuse of this kind of technology. == Applications == Personality computing techniques, in particular personality recognition and perception, have applications in Social media marketing, where they can help reducing the cost of advertising campaigns through psychological targeting.

  Read more →
• 

  Kernel density estimation

  In statistics, kernel density estimation (KDE) is the application of kernel smoothing for probability density estimation, i.e., a non-parametric method to estimate the probability density function of a random variable based on kernels as weights. KDE answers a fundamental data smoothing problem where inferences about the population are made based on a finite data sample. In some fields such as signal processing and econometrics it is also termed the Parzen–Rosenblatt window method, after Emanuel Parzen and Murray Rosenblatt, who are usually credited with independently creating it in its current form. One of the famous applications of kernel density estimation is in estimating the class-conditional marginal densities of data when using a naive Bayes classifier, which can improve its prediction accuracy. == Definition == Let x = ( x 1 , x 2 , x 3 , . . . ) {\displaystyle \mathbf {x} =\left(x_{1},x_{2},x_{3},...\right)} be independent and identically distributed samples drawn from some univariate distribution with an unknown density f at any given point x. We are interested in estimating the shape of this function f. Its kernel density estimator is f ^ h ( x ) = 1 n ∑ i = 1 n K h ( x − x i ) = 1 n h ∑ i = 1 n K ( x − x i h ) , {\displaystyle {\hat {f}}_{h}(x)={\frac {1}{n}}\sum _{i=1}^{n}K_{h}(x-x_{i})={\frac {1}{nh}}\sum _{i=1}^{n}K{\left({\frac {x-x_{i}}{h}}\right)},} where K is the kernel — a non-negative function — and h > 0 is a smoothing parameter called the bandwidth or simply width. A kernel with subscript h is called the scaled kernel and defined as Kh(x) = ⁠1/h⁠ K(⁠x/h⁠). Intuitively one wants to choose h as small as the data will allow; however, there is always a trade-off between the bias of the estimator and its variance. The choice of bandwidth is discussed in more detail below. A range of kernel functions are commonly used: uniform, triangular, biweight, triweight, Epanechnikov (parabolic), normal, and others. The Epanechnikov kernel is optimal in a mean square error sense, though the loss of efficiency is small for the kernels listed previously. Due to its convenient mathematical properties, the normal kernel is often used, which means K(x) = ϕ(x), where ϕ is the standard normal density function. The kernel density estimator then becomes f ^ h ( x ) = 1 n ∑ i = 1 n 1 h 2 π exp ⁡ ( − ( x − x i ) 2 2 h 2 ) , {\displaystyle {\hat {f}}_{h}(x)={\frac {1}{n}}\sum _{i=1}^{n}{\frac {1}{h{\sqrt {2\pi }}}}\exp \left({\frac {-(x-x_{i})^{2}}{2h^{2}}}\right),} where h {\displaystyle h} is the standard deviation of the sample x {\displaystyle \mathbf {x} } . The construction of a kernel density estimate finds interpretations in fields outside of density estimation. For example, in thermodynamics, this is equivalent to the amount of heat generated when heat kernels (the fundamental solution to the heat equation) are placed at each data point locations xi. Similar methods are used to construct discrete Laplace operators on point clouds for manifold learning (e.g. diffusion map). == Example == Kernel density estimates are closely related to histograms, but can be endowed with properties such as smoothness or continuity by using a suitable kernel. The diagram below based on these 6 data points illustrates this relationship: For the histogram, first, the horizontal axis is divided into sub-intervals or bins which cover the range of the data: In this case, six bins each of width 2. Whenever a data point falls inside this interval, a box of height 1/12 is placed there. If more than one data point falls inside the same bin, the boxes are stacked on top of each other. For the kernel density estimate, normal kernels with a standard deviation of 1.5 (indicated by the red dashed lines) are placed on each of the data points xi. The kernels are summed to make the kernel density estimate (solid blue curve). The smoothness of the kernel density estimate (compared to the discreteness of the histogram) illustrates how kernel density estimates converge faster to the true underlying density for continuous random variables. == Bandwidth selection == The bandwidth of the kernel is a free parameter which exhibits a strong influence on the resulting estimate. To illustrate its effect, we take a simulated random sample from the standard normal distribution (plotted at the blue spikes in the rug plot on the horizontal axis). The grey curve is the true density (a normal density with mean 0 and variance 1). In comparison, the red curve is undersmoothed since it contains too many spurious data artifacts arising from using a bandwidth h = 0.05, which is too small. The green curve is oversmoothed since using the bandwidth h = 2 obscures much of the underlying structure. The black curve with a bandwidth of h = 0.337 is considered to be optimally smoothed since its density estimate is close to the true density. An extreme situation is encountered in the limit h → 0 {\displaystyle h\to 0} (no smoothing), where the estimate is a sum of n delta functions centered at the coordinates of analyzed samples. In the other extreme limit h → ∞ {\displaystyle h\to \infty } the estimate retains the shape of the used kernel, centered on the mean of the samples (completely smooth). The most common optimality criterion used to select this parameter is the expected L2 risk function, also termed the mean integrated squared error: MISE ⁡ ( h ) = E [ ∫ ( f ^ h ( x ) − f ( x ) ) 2 d x ] {\displaystyle \operatorname {MISE} (h)=\operatorname {E} \!\left[\int \!{\left({\hat {f}}\!_{h}(x)-f(x)\right)}^{2}dx\right]} Under weak assumptions on f and K, (f is the, generally unknown, real density function), MISE ⁡ ( h ) = AMISE ⁡ ( h ) + o ( ( n h ) − 1 + h 4 ) {\displaystyle \operatorname {MISE} (h)=\operatorname {AMISE} (h)+{\mathcal {o}}{\left((nh)^{-1}+h^{4}\right)}} where o is the little o notation, and n the sample size (as above). The AMISE is the asymptotic MISE, i. e. the two leading terms, AMISE ⁡ ( h ) = R ( K ) n h + 1 4 m 2 ( K ) 2 h 4 R ( f ″ ) {\displaystyle \operatorname {AMISE} (h)={\frac {R(K)}{nh}}+{\frac {1}{4}}m_{2}(K)^{2}h^{4}R(f'')} where R ( g ) = ∫ g ( x ) 2 d x {\textstyle R(g)=\int g(x)^{2}\,dx} for a function g, m 2 ( K ) = ∫ x 2 K ( x ) d x {\textstyle m_{2}(K)=\int x^{2}K(x)\,dx} and f ″ {\displaystyle f''} is the second derivative of f {\displaystyle f} and K {\displaystyle K} is the kernel. The minimum of this AMISE is the solution to this differential equation ∂ ∂ h AMISE ⁡ ( h ) = − R ( K ) n h 2 + m 2 ( K ) 2 h 3 R ( f ″ ) = 0 {\displaystyle {\frac {\partial }{\partial h}}\operatorname {AMISE} (h)=-{\frac {R(K)}{nh^{2}}}+m_{2}(K)^{2}h^{3}R(f'')=0} or h AMISE = R ( K ) 1 / 5 m 2 ( K ) 2 / 5 R ( f ″ ) 1 / 5 n − 1 / 5 = C n − 1 / 5 {\displaystyle h_{\operatorname {AMISE} }={\frac {R(K)^{1/5}}{m_{2}(K)^{2/5}R(f'')^{1/5}}}n^{-1/5}=Cn^{-1/5}} Neither the AMISE nor the hAMISE formulas can be used directly since they involve the unknown density function f {\displaystyle f} or its second derivative f ″ {\displaystyle f''} . To overcome that difficulty, a variety of automatic, data-based methods have been developed to select the bandwidth. Several review studies have been undertaken to compare their efficacies, with the general consensus that the plug-in selectors and cross validation selectors are the most useful over a wide range of data sets. Substituting any bandwidth h which has the same asymptotic order n−1/5 as hAMISE into the AMISE gives that AMISE(h) = O(n−4/5), where O is the big O notation. It can be shown that, under weak assumptions, there cannot exist a non-parametric estimator that converges at a faster rate than the kernel estimator. Note that the n−4/5 rate is slower than the typical n−1 convergence rate of parametric methods. If the bandwidth is not held fixed, but is varied depending upon the location of either the estimate (balloon estimator) or the samples (pointwise estimator), this produces a particularly powerful method termed adaptive or variable bandwidth kernel density estimation. Bandwidth selection for kernel density estimation of heavy-tailed distributions is relatively difficult. === A rule-of-thumb bandwidth estimator === If Gaussian basis functions are used to approximate univariate data, and the underlying density being estimated is Gaussian, the optimal choice for h (that is, the bandwidth that minimises the mean integrated squared error) is: h = ( 4 σ ^ 5 3 n ) 1 / 5 ≈ 1.06 σ ^ n − 1 / 5 , {\displaystyle h={\left({\frac {4{\hat {\sigma }}^{5}}{3n}}\right)}^{1/5}\approx 1.06\,{\hat {\sigma }}\,n^{-1/5},} An h {\displaystyle h} value is considered more robust when it improves the fit for long-tailed and skewed distributions or for bimodal mixture distributions. This is often done empirically by replacing the standard deviation σ ^ {\displaystyle {\hat {\sigma }}} by the parameter A {\displaystyle A} below: A = min ( σ ^ , I Q R 1.34 ) {\displaystyle A=\min \left({\hat {\sigma }},{\frac {\mathrm {IQR} }{1.34}}\right)} where IQR is the

  Read more →
• 

  Grokking (machine learning)

  In machine learning, grokking, or delayed generalization, is a phenomenon observed in some settings where a model abruptly transitions from overfitting (performing well only on training data) to generalizing (performing well on both training and test data), after many training iterations with little or no improvement on the held-out data. This contrasts with what is typically observed in machine learning, where generalization occurs gradually alongside improved performance on training data. == Origin == Grokking was introduced by OpenAI researcher Alethea Power and colleagues in the January 2022 paper "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets". It is derived from the word grok coined by Robert Heinlein in his novel Stranger in a Strange Land. In ML research, "grokking" is not used as a synonym for "generalization"; rather, it names a sometimes-observed delayed‑generalization training phenomenon in which training and held‑out performance do not improve in tandem, and in which held‑out performance rises abruptly later. Authors also analyze the "grokking time", the epoch or step at which this transition occurs in those scenarios. == Interpretations == Grokking can be understood as a phase transition during the training process. In particular, recent work has shown that grokking may be due to a complexity phase transition in the model during training. While grokking has been thought of as largely a phenomenon of relatively shallow models, grokking has been observed in deep neural networks and non-neural models and is the subject of active research. One potential explanation is that the weight decay (a component of the loss function that penalizes higher values of the neural network parameters, also called regularization) slightly favors the general solution that involves lower weight values, but that is also harder to find. According to Neel Nanda, the process of learning the general solution may be gradual, even though the transition to the general solution occurs more suddenly later. Recent theories have hypothesized that grokking occurs when neural networks transition from a "lazy training" regime where the weights do not deviate far from initialization, to a "rich" regime where weights abruptly begin to move in task-relevant directions. Follow-up empirical and theoretical work has accumulated evidence in support of this perspective, and it offers a unifying view of earlier work as the transition from lazy to rich training dynamics is known to arise from properties of adaptive optimizers, weight decay, initial parameter weight norm, and more. This perspective is complementary to a unifying "pattern learning speeds" framework that links grokking and double descent; within this view, delayed generalization can arise across training time ("epoch‑wise") or across model size ("model‑wise"), and the authors report "model‑wise grokking".

  Read more →
• 

  Capture the flag (cybersecurity)

  In computer security, Capture the Flag (CTF) is an exercise in which participants attempt to find text strings, called "flags", which are secretly hidden in purposefully vulnerable programs or websites. They can be used for both competitive or educational purposes. In two main variations of CTFs, participants either steal flags from other participants (attack/defense-style CTFs) or from organizers (jeopardy-style challenges). A mixed competition combines these two styles. Competitions can include hiding flags in hardware devices, they can be both online or in-person, and can be advanced or entry-level. The game is inspired by the traditional outdoor sport with the same name. CTFs are used as a tool for developing and refining cybersecurity skills, making them popular in both professional and academic settings. == Overview == Capture the Flag (CTF) is a cybersecurity competition that is used to test and develop computer security skills. It was first developed in 1996 at DEF CON, the largest cybersecurity conference in the United States which is hosted annually in Las Vegas, Nevada. The conference hosts a weekend of cybersecurity competitions, including their flagship CTF. Two popular CTF formats are jeopardy and attack-defense. Both formats test participant’s knowledge in cybersecurity, but differ in objective. In the Jeopardy format, participating teams must complete as many challenges of varying point values from a various categories such as cryptography, web exploitation, and reverse engineering. In the attack-defense format, competing teams must defend their vulnerable computer systems while attacking their opponent's systems. The exercise involves a diverse array of tasks, including exploitation and cracking passwords, but there is little evidence showing how these tasks translate into cybersecurity knowledge held by security experts. Recent research has shown that the Capture the Flag tasks mainly covered technical knowledge but lacked social topics like social engineering and awareness on cybersecurity. == Educational applications == CTFs have been shown to be an effective way to improve cybersecurity education through gamification. There are many examples of CTFs designed to teach cybersecurity skills to a wide variety of audiences, including PicoCTF, organized by the Carnegie Mellon CyLab, which is oriented towards high school students, and Arizona State University supported pwn.college. Beyond educational CTF events and resources, CTFs has been shown to be a highly effective way to instill cybersecurity concepts in the classroom. CTFs have been included in undergraduate computer science classes such as Introduction to Information Security at the National University of Singapore. CTFs are also popular in military academies. They are often included as part of the curriculum for cybersecurity courses, with the NSA organized Cyber Exercise culminating in a CTF competition between the US service academies and military colleges. == Competitions == Many CTF organizers register their competition with the CTFtime platform. This allows the tracking of the position of teams over time and across competitions. These include "Plaid Parliament of Pwning", "More Smoked Leet Chicken", "Dragon Sector", "dcua", "Eat, Sleep, Pwn, Repeat", "perfect blue", "organizers" and "Blue Water". Overall the "Plaid Parliament of Pwning" and "Dragon Sector" have both placed first worldwide the most with three times each. === Community competitions === Every year there are dozens of CTFs organized in a variety of formats. Many CTFs are associated with cybersecurity conferences such as DEF CON, various editions of SANS Institute's NetWars, HITCON, and BSides. The DEF CON CTF, an attack-defence CTF, is notable for being one of the oldest CTF competitions to exist, and has been variously referred to as the "World Series", "Superbowl", and "Olympics", of hacking by media outlets. The NYU Tandon hosted Cybersecurity Awareness Worldwide (CSAW) CTF is one of the largest open-entry competitions for students learning cybersecurity from around the world. In 2021, it hosted over 1200 teams during the qualification round. In addition to conference organized CTFs, many CTF clubs and teams organize CTF competitions. Many CTF clubs and teams are associated with universities, such as the CMU associated Plaid Parliament of Pwning, which hosts PlaidCTF, and the ASU associated Shellphish. Some community CTFs are online and open to all participants. The SANS Institute Holiday Hack Challenge and TryHackMe Advent of Cyber. === Government-supported competitions === Governmentally supported CTF competitions include the DARPA Cyber Grand Challenge and ENISA European Cybersecurity Challenge. In 2023, the US Space Force-sponsored Hack-a-Sat CTF competition included, for the first time, a live orbital satellite for participants to exploit. === Corporate-supported competitions === Corporations and other organizations sometimes use CTFs as a training or evaluation exercise, with benefits similar to those in educational settings. In addition to internal CTF exercises, some corporations such as Google and Tencent host publicly accessible CTF competitions. == In popular culture == In Mr. Robot, a qualification round for the DEF CON CTF competition is depicted in the season 3 opener "eps3.0_power-saver-mode.h". The logo for DEF CON can be seen in the background. In The Undeclared War, a CTF is depicted in the opening scene of the series as a recruitment exercise used by GCHQ. Go Go Squid!, a Chinese television series, is based around training for and competing in highly stylized CTF competitions .

  Read more →
• 

  TensorFlow Hub

  TensorFlow Hub (also styled TF Hub) is an open-source machine learning library and online repository that provides TensorFlow model components, called modules. It is maintained by Google as part of the TensorFlow ecosystem and allows developers to discover, publish, and reuse pretrained models for tasks such as computer vision, natural language processing, and transfer learning. == Overview == TensorFlow Hub provides a central platform where developers and researchers can access pre-trained models and integrate them directly into TensorFlow workflows. Each module encapsulates a computation graph and its trained weights, with standardized input and output signatures. Modules can be loaded using the hub.load() function or through Keras integration via hub.KerasLayer, enabling users to perform transfer learning or feature extraction. == History == TensorFlow Hub was announced by Google in March 2018, with the first public version released shortly after. Its introduction coincided with the growing adoption of transfer learning techniques and the need for standardized model packaging. Over time, the hub expanded to include models such as the BERT family, MobileNet, EfficientNet, and the Universal Sentence Encoder. In 2020, research on “Regret selection in TensorFlow Hub” explored the problem of identifying optimal models for downstream tasks given a large repository of alternatives. == Applications == TensorFlow Hub hosts a variety of models across machine learning domains: Natural language processing: BERT, ALBERT language model, and Universal Sentence Encoder. Computer vision: ResNet, Inception (deep learning), MobileNet, EfficientNet. Speech and audio: spectrogram feature extractors and automatic speech recognition models. Multilingual embeddings: cross-lingual and sentence-level representations for machine translation and semantic similarity. Modules are widely used in education, academic research, and industry for prototyping and production deployment.

  Read more →
• 

  Tensor (machine learning)

  In machine learning, the term tensor informally refers to two different concepts: (i) a way of organizing data and (ii) a multilinear (tensor) transformation. Data may be organized in a multidimensional array (M-way array), informally referred to as a "data tensor"; however, in the strict mathematical sense, a tensor is a multilinear mapping over a set of domain vector spaces to a range vector space. Observations, such as images, movies, volumes, sounds, and relationships among words and concepts, stored in an M-way array ("data tensor"), may be analyzed either by artificial neural networks or tensor methods. Tensor decomposition factors data tensors into smaller tensors. Operations on data tensors can be expressed in terms of matrix multiplication and the Kronecker product. The computation of gradients, a crucial aspect of backpropagation, can be performed using software libraries such as PyTorch and TensorFlow. Computations are often performed on graphics processing units (GPUs) using CUDA, and on dedicated hardware such as Google's Tensor Processing Unit or Nvidia's Tensor core. These developments have greatly accelerated neural network architectures, and increased the size and complexity of models that can be trained. == History == A tensor is by definition a multilinear map. In mathematics, this may express a multilinear relationship between sets of algebraic objects. In physics, tensor fields, considered as tensors at each point in space, are useful in expressing mechanics such as stress or elasticity. In machine learning, the exact use of tensors depends on the statistical approach being used. In 2001, the field of signal processing and statistics were making use of tensor methods. Pierre Comon surveys the early adoption of tensor methods in the fields of telecommunications, radio surveillance, chemometrics and sensor processing. Linear tensor rank methods (such as, Parafac/CANDECOMP) analyzed M-way arrays ("data tensors") composed of higher order statistics that were employed in blind source separation problems to compute a linear model of the data. He noted several early limitations in determining the tensor rank and efficient tensor rank decomposition. In the early 2000s, multilinear tensor methods crossed over into computer vision, computer graphics and machine learning with papers by Vasilescu or in collaboration with Terzopoulos, such as Human Motion Signatures, TensorFaces TensorTextures and Multilinear Projection. Multilinear algebra, the algebra of higher-order tensors, is a suitable and transparent framework for analyzing the multifactor structure of an ensemble of observations and for addressing the difficult problem of disentangling the causal factors based on second order or higher order statistics associated with each causal factor. Tensor (multilinear) factor analysis disentangles and reduces the influence of different causal factors with multilinear subspace learning. When treating an image or a video as a 2- or 3-way array, i.e., "data matrix/tensor", tensor methods reduce spatial or time redundancies as demonstrated by Wang and Ahuja. Yoshua Bengio, Geoff Hinton and their collaborators briefly discuss the relationship between deep neural networks and tensor factor analysis beyond the use of M-way arrays ("data tensors") as inputs. One of the early uses of tensors for neural networks appeared in natural language processing. A single word can be expressed as a vector via Word2vec. Thus a relationship between two words can be encoded in a matrix. However, for more complex relationships such as subject-object-verb, it is necessary to build higher-dimensional networks. In 2009, the work of Sutskever introduced Bayesian Clustered Tensor Factorization to model relational concepts while reducing the parameter space. From 2014 to 2015, tensor methods become more common in convolutional neural networks (CNNs). Tensor methods organize neural network weights in a "data tensor", analyze and reduce the number of neural network weights. Lebedev et al. accelerated CNN networks for character classification (the recognition of letters and digits in images) by using 4D kernel tensors. == Definition == Let F {\displaystyle \mathbb {F} } be a field (such as the real numbers R {\displaystyle \mathbb {R} } or the complex numbers C {\displaystyle \mathbb {C} } ). A tensor T ∈ F I 1 × I 2 × … × I C {\displaystyle {\mathcal {T}}\in {\mathbb {F} }^{I_{1}\times I_{2}\times \ldots \times I_{C}}} is a multilinear transformation from a set of domain vector spaces to a range vector space: T : { F I 1 × F I 2 × … F I C } ↦ F I 0 {\displaystyle {\mathcal {T}}:\{{\mathbb {F} }^{I_{1}}\times {\mathbb {F} }^{I_{2}}\times \ldots {\mathbb {F} }^{I_{C}}\}\mapsto {\mathbb {F} }^{I_{0}}} Here, C {\displaystyle C} and I 0 , I 1 , … , I C {\displaystyle I_{0},I_{1},\ldots ,I_{C}} are positive integers, and ( C + 1 ) {\displaystyle (C+1)} is the number of modes of a tensor (also known as the number of ways of a multi-way array). The dimensionality of mode c {\displaystyle c} is I c {\displaystyle I_{c}} , for 0 ≤ c ≤ C {\displaystyle 0\leq c\leq C} . In statistics and machine learning, an image is vectorized when viewed as a single observation, and a collection of vectorized images is organized as a "data tensor". For example, a set of facial images { d i p , i e , i l , i v ∈ R I X } {\displaystyle \{{\mathbb {d} }_{i_{p},i_{e},i_{l},i_{v}}\in {\mathbb {R} }^{I_{X}}\}} with I X {\displaystyle I_{X}} pixels that are the consequences of multiple causal factors, such as a facial geometry i p ( 1 ≤ i p ≤ I P ) {\displaystyle i_{p}(1\leq i_{p}\leq I_{P})} , an expression i e ( 1 ≤ i e ≤ I E ) {\displaystyle i_{e}(1\leq i_{e}\leq I_{E})} , an illumination condition i l ( 1 ≤ i l ≤ I L ) {\displaystyle i_{l}(1\leq i_{l}\leq I_{L})} , and a viewing condition i v ( 1 ≤ i v ≤ I V ) {\displaystyle i_{v}(1\leq i_{v}\leq I_{V})} may be organized into a data tensor (ie. multiway array) D ∈ R I X × I P × I E × I L × V {\displaystyle {\mathcal {D}}\in {\mathbb {R} }^{I_{X}\times I_{P}\times I_{E}\times I_{L}\times V}} where I P {\displaystyle I_{P}} are the total number of facial geometries, I E {\displaystyle I_{E}} are the total number of expressions, I L {\displaystyle I_{L}} are the total number of illumination conditions, and I V {\displaystyle I_{V}} are the total number of viewing conditions. Tensor factorizations methods such as TensorFaces and multilinear (tensor) independent component analysis factorizes the data tensor into a set of vector spaces that span the causal factor representations, where an image is the result of tensor transformation T {\displaystyle {\mathcal {T}}} that maps a set of causal factor representations to the pixel space. Another approach to using tensors in machine learning is to embed various data types directly. For example, a grayscale image, commonly represented as a discrete 2-way array D ∈ R I R X × I C X {\displaystyle {\mathbf {D} }\in {\mathbb {R} }^{I_{RX}\times I_{CX}}} with dimensionality I R X × I C X {\displaystyle I_{RX}\times I_{CX}} where I R X {\displaystyle I_{RX}} are the number of rows and I C X {\displaystyle I_{CX}} are the number of columns. When an image is treated as 2-way array or 2nd order tensor (i.e. as a collection of column/row observations), tensor factorization methods compute the image column space, the image row space and the normalized PCA coefficients or the ICA coefficients. Similarly, a color image with RGB channels, D ∈ R N × M × 3 . {\displaystyle {\mathcal {D}}\in \mathbb {R} ^{N\times M\times 3}.} may be viewed as a 3rd order data tensor or 3-way array.-------- In natural language processing, a word might be expressed as a vector v {\displaystyle v} via the Word2vec algorithm. Thus v {\displaystyle v} becomes a mode-1 tensor v ↦ A ∈ R N . {\displaystyle v\mapsto {\mathcal {A}}\in \mathbb {R} ^{N}.} The embedding of subject-object-verb semantics requires embedding relationships among three words. Because a word is itself a vector, subject-object-verb semantics could be expressed using mode-3 tensors v a × v b × v c ↦ A ∈ R N × N × N . {\displaystyle v_{a}\times v_{b}\times v_{c}\mapsto {\mathcal {A}}\in \mathbb {R} ^{N\times N\times N}.} In practice the neural network designer is primarily concerned with the specification of embeddings, the connection of tensor layers, and the operations performed on them in a network. Modern machine learning frameworks manage the optimization, tensor factorization and backpropagation automatically. === As unit values === Tensors may be used as the unit values of neural networks which extend the concept of scalar, vector and matrix values to multiple dimensions. The output value of single layer unit y m {\displaystyle y_{m}} is the sum-product of its input units and the connection weights filtered through the activation function f {\displaystyle f} : y m = f ( ∑ n x n u m , n ) , {\displaystyle y_{m}=f\left(\sum _{n}x_{n}u_{m,n}\right),} where y m ∈ R .

  Read more →
• 

  Learning automaton

  A learning automaton is one type of machine learning algorithm studied since 1970s. Learning automata select their current action based on past experiences from the environment. It will fall into the range of reinforcement learning if the environment is stochastic and a Markov decision process (MDP) is used. == History == Research in learning automata can be traced back to the work of Michael Lvovitch Tsetlin in the early 1960s in the Soviet Union. Together with some colleagues, he published a collection of papers on how to use matrices to describe automata functions. Additionally, Tsetlin worked on reasonable and collective automata behaviour, and on automata games. Learning automata were also investigated by researches in the United States in the 1960s. However, the term learning automaton was not used until Narendra and Thathachar introduced it in a survey paper in 1974. == Definition == A learning automaton is an adaptive decision-making unit situated in a random environment that learns the optimal action through repeated interactions with its environment. The actions are chosen according to a specific probability distribution which is updated based on the environment response the automaton obtains by performing a particular action. With respect to the field of reinforcement learning, learning automata are characterized as policy iterators. In contrast to other reinforcement learners, policy iterators directly manipulate the policy π. Another example for policy iterators are evolutionary algorithms. Formally, Narendra and Thathachar define a stochastic automaton to consist of: a set X of possible inputs, a set Φ = { Φ1, ..., Φs } of possible internal states, a set α = { α1, ..., αr } of possible outputs, or actions, with r ≤ s, an initial state probability vector p(0) = ≪ p1(0), ..., ps(0) ≫, a computable function A which after each time step t generates p(t+1) from p(t), the current input, and the current state, and a function G: Φ → α which generates the output at each time step. In their paper, they investigate only stochastic automata with r = s and G being bijective, allowing them to confuse actions and states. The states of such an automaton correspond to the states of a "discrete-state discrete-parameter Markov process". At each time step t=0,1,2,3,..., the automaton reads an input from its environment, updates p(t) to p(t+1) by A, randomly chooses a successor state according to the probabilities p(t+1) and outputs the corresponding action. The automaton's environment, in turn, reads the action and sends the next input to the automaton. Frequently, the input set X = { 0,1 } is used, with 0 and 1 corresponding to a nonpenalty and a penalty response of the environment, respectively; in this case, the automaton should learn to minimize the number of penalty responses, and the feedback loop of automaton and environment is called a "P-model". More generally, a "Q-model" allows an arbitrary finite input set X, and an "S-model" uses the interval [0,1] of real numbers as X. A visualised demo/ Art Work of a single Learning Automaton had been developed by μSystems (microSystems) Research Group at Newcastle University. == Finite action-set learning automata == Finite action-set learning automata (FALA) are a class of learning automata for which the number of possible actions is finite or, in more mathematical terms, for which the size of the action-set is finite.

  Read more →
• 

  List of software palettes

  This is a list of software palettes used by computers. Systems that use a 4-bit or 8-bit pixel depth can display up to 16 or 256 colors simultaneously. Many personal computers in the early 1990s displayed at most 256 different colors, freely selected by software (either by the user or by a program) from their wider hardware's RGB color palette. Usual selections of colors in limited subsets (generally 16 or 256) of the full palette includes some RGB level arrangements commonly used with the 8-bit palettes as master palettes or universal palettes (i.e., palettes for multipurpose uses). These are some representative software palettes, but any selection can be made in such of systems. For specific hardware color palettes, see the list of monochrome and RGB palettes, list of 8-bit computer hardware graphics, the list of 16-bit computer hardware graphics and the list of video game console palettes articles. Each palette is represented by an array of color patches. A one-pixel size version appears below each palette, to make it easy to compare palette sizes. 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 8-bit, 256 levels of the red, green, and blue (RGB) primary colors and cyan, magenta, and yellow complementary colors, along with a full 8-bit, 256 levels 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. == System specifics == These are selections of colors officially employed as system palettes in some popular operating systems for personal computers that support 8-bit displays. === Microsoft Windows and IBM OS/2 default 16-color palette === Used by these platforms as a roughly backward compatible palette for the CGA, EGA and VGA text modes, but with colors arranged in a different order. Also, is the default palette for 16 color icons. The corresponding indices into this palette are: === Microsoft Windows default 20-color palette === In 256-color mode, there are four additional standard Windows colors, twenty system reserved colors in total; thus the system leaves 236 palette indexes free for applications to use. The system color entries inside a 256-color palette table are the first ten plus the last ten. In any case, the additional system colors do not seem to add a sharp color richness: they are only some intermediate shades of grayish colors. Since Windows 95, these additional colors can be changed by the system when a color scheme needs custom colors, reducing their utility as static, unchanging palette entries. The complete 20-color Windows system palette is: === Apple Macintosh default 16-color palette === When Apple Computer introduced the Macintosh II in 1987, this 16-color palette was included in System 4.1. === RISC OS default palette === Acorn RISC OS 2.x and 3.x provided this 16-color palette: === Solaris default 16-color palette === Solaris OS used this color palette: == RGB arrangements == These are selections of colors based in evenly ordered RGB levels which provide complete RGB combinations, mainly used as master palettes to display any kind of image within the limitations of the 8-bit pixel depth. === 6 level RGB === Having six levels for every primary, with 6³ = 216 combinations. The index can be addressed by (36×R)+(6×G)+B, with all R, G and B values in a range from 0 to 5. Intended as homogeneous RGB cube, it gives six true grays. Also, there is room for another sorts of 40 colors, so operating systems or programs can add extra colors. Systems that use this software palette are: Web-safe colors Apple Macintosh 256 color default palette. It also contains four gradients of ten shades each for gray, red, green and blue. === 6-7-6 levels RGB === This palette is constructed with six levels for red and blue primaries and seven levels for the green primary, giving 6×7×6 = 252 combinations. The index can be addressed by (42×R)+(6×G)+B, with R and B values in a range from 0 to 5 and G in a range from 0 to 6. The same case as the former, but with an added level of green due to the greater sensibility of the normal human eye to this frequency. It does not provide true grays, but remaining indexes can be filled with four intermediate grays. In any case, there is little room for any other color. === 6-8-5 levels RGB === This palette is constructed with six levels for red, eight levels for green and five levels for the blue primaries, giving 6×8×5 = 240 combinations. The index can be addressed by (40×R)+(5×G)+B, with R ranging from 0 to 5, G from 0 to 7 and B from 0 to 4. Levels are chosen in function of sensibility of the normal human eye to every primary color. Also, it does not provide true grays. Remaining indexes can be filled with sixteen intermediate grays or other fixed colors. In fact, this is the best balanced RGB master software palette, in a compromise between the RGB arrangement based in the human eye's sensibility and a sufficient remaining palette entries for another purposes. === 8-8-4 levels RGB === The 8-8-4 level RGB use eight levels for each of the red and green color components (3+3 high order bits), and four levels (2 low order bits) for the blue component, due to the lesser sensitivity of the normal human eye to this primary color. This results in an 8×8×4 = 256-color palette as follows: This RGB software palette occupies the full 8-bit range of possible palette entries, so there is no room for other fixed colors. Software using this palette must draw their user interface elements with the same colors used to show pictures. Also again, it does not provide true grays. == Other common uses of software palettes == === Grayscale palettes === Simple palette made doing every triplet RGB primaries having equal values as a continuous gradient from black to white through the full available palette entries. Here is the 8-bit, 256 levels palette: Used to display pure grayscale TIFF or JPEG images, for example. === Color gradient palettes === Palettes made of a continuous color gradient from darkest to lightest arbitrary hues. The pixel data is treated as if it were grayscale, but the color table plays with RGB color combinations, not only gray. The relationship between the original luminance and the mapped one can vary, but the lighting scale is preserved along all the palette entries. One very common case of such palettes is the sepia tone palette, which gives an image an old fashioned and aged look (left). Another gradient example, based on blue hues, is presented here (right), but any hue or mixing of hues can be used. Many cell phones with built-in cameras have options to take colorized photos using this technique. === Adaptive palettes === Those whose whole number of available indexes are filled with RGB combinations selected from the statistical order of appearance (usually balanced) of a concrete full true color original image. There exist many algorithms to pick the colors through color quantization; one well known is the Heckbert's median-cut algorithm. Here is the 8-bit, 256 color palette used with the color test chart and the image sample above: Adaptive palettes only work well with a unique image. Trying to display different images with adaptive palettes over an 8-bit display usually results in only one image with correct colors, because the images have different palettes and only one can be displayed at a time. Here is an example of what happens when an indexed color image is displayed with any color palette that is not its own adaptive palette: === False color palettes === Arbitrary gradient color scales, usually 256 shades, with no relationship with real colors of a given image. They are employed to artificially colorize a grayscale image to reveal details and/or to map the pixel level values to amounts of some physical magnitude (potential, temperature, altitude, etc.) Note, in the example above, that new details can be seen as blue over magenta in the background's dark areas of the original photograph. Here is the 8-bit, 256 color gradient palette used with the color test chart and the image sample above: There exist many false color palettes, some of them standardized, used mainly in scientific applications: astronomy and radioastronomy, satellite land imaging, thermography, study of materials, tomography and magnetic resonance imaging in medicine, etc.

  Read more →
• 

  Self-management (computer science)

  Self-management is the process by which computer systems manage their own operation without human intervention. Self-management technologies are expected to pervade the next generation of network management systems. The growing complexity of modern networked computer systems is a limiting factor in their expansion. The increasing heterogeneity of corporate computer systems, the inclusion of mobile computing devices, and the combination of different networking technologies like WLAN, cellular phone networks, and mobile ad hoc networks make the conventional, manual management difficult, time-consuming, and error-prone. More recently, self-management has been suggested as a solution to increasing complexity in cloud computing. An industrial initiative towards realizing self-management is the Autonomic Computing Initiative (ACI) started by IBM in 2001. The ACI defines the following four functional areas: Self-configuration Auto-configuration of components Self-healing Automatic discovery, and correction of faults; automatically applying all necessary actions to bring system back to normal operation Self-optimization Automatic monitoring and control of resources to ensure the optimal functioning with respect to the defined requirements Self-protection Proactive identification and protection from arbitrary attacks

  Read more →
• 

  Leakage (machine learning)

  In statistics and machine learning, leakage (also known as data leakage or target leakage) refers to the use of information during model training that would not be available at prediction time. This results in overly optimistic performance estimates, as the model appears to perform better during evaluation than it actually would in a production environment. Leakage is often subtle and indirect, making it difficult to detect and eliminate. It can lead a statistician or modeler to select a suboptimal model, which may be outperformed by a leakage-free alternative. == Leakage modes == Leakage can occur at multiple stages of the machine learning workflow. Broadly, its sources can be divided into two categories: those arising from features and those arising from training examples. === Feature leakage === Feature or column-wise leakage is caused by the inclusion of columns which are one of the following: a duplicate label, a proxy for the label, or the label itself. These features, known as anachronisms, will not be available when the model is used for predictions, and result in leakage if included when the model is trained. For example, including a "MonthlySalary" column when predicting "YearlySalary"; or "MinutesLate" when predicting "IsLate". === Training example leakage === Row-wise leakage is caused by improper sharing of information between rows of data. Types of row-wise leakage include: Premature featurization; leaking from premature featurization before Cross-validation/Train/Test split (must fit MinMax/ngrams/etc on only the train split, then transform the test set) Duplicate rows between train/validation/test (for example, oversampling a dataset to pad its size before splitting; or, different rotations/augmentations of a single image; bootstrap sampling before splitting; or duplicating rows to up sample the minority class) Non-independent and identically distributed random (non-IID) data Time leakage (for example, splitting a time-series dataset randomly instead of newer data in test set using a train/test split or rolling-origin cross-validation) Group leakage—not including a grouping split column (for example, Andrew Ng's group had 100k x-rays of 30k patients, meaning ~3 images per patient. The paper used random splitting instead of ensuring that all images of a patient were in the same split. Hence the model partially memorized the patients instead of learning to recognize pneumonia in chest x-rays.) A 2023 review found data leakage to be "a widespread failure mode in machine-learning (ML)-based science", having affected at least 294 academic publications across 17 disciplines, and causing a potential reproducibility crisis. == Detection == Data leakage in machine learning can be detected through various methods, focusing on performance analysis, feature examination, data auditing, and model behavior analysis. Performance-wise, unusually high accuracy or significant discrepancies between training and test results often indicate leakage. Inconsistent cross-validation outcomes may also signal issues. Feature examination involves scrutinizing feature importance rankings and ensuring temporal integrity in time series data. A thorough audit of the data pipeline is crucial, reviewing pre-processing steps, feature engineering, and data splitting processes. Detecting duplicate entries across dataset splits is also important. For language models, the Min-K% method can detect the presence of data in a pretraining dataset. It presents a sentence suspected to be present in the pretraining dataset, and computes the log-likelihood of each token, then compute the average of the lowest K of these. If this exceeds a threshold, then the sentence is likely present. This method is improved by comparing against a baseline of the mean and variance. Analyzing model behavior can reveal leakage. Models relying heavily on counter-intuitive features or showing unexpected prediction patterns warrant investigation. Performance degradation over time when tested on new data may suggest earlier inflated metrics due to leakage. Advanced techniques include backward feature elimination, where suspicious features are temporarily removed to observe performance changes. Using a separate hold-out dataset for final validation before deployment is advisable.

  Read more →
• 

  Manifold hypothesis

  The manifold hypothesis posits that many high-dimensional data sets that occur in the real world actually lie along low-dimensional latent manifolds inside that high-dimensional space. As a consequence of the manifold hypothesis, many data sets that appear to initially require many variables to describe, can actually be described by a comparatively small number of variables, linked to the local coordinate system of the underlying manifold. It is suggested that this principle underpins the effectiveness of machine learning algorithms in describing high-dimensional data sets by considering a few common features. The manifold hypothesis is related to the effectiveness of nonlinear dimensionality reduction techniques in machine learning. Many techniques of dimensional reduction make the assumption that data lies along a low-dimensional submanifold, such as manifold sculpting, manifold alignment, and manifold regularization. The major implications of this hypothesis is that Machine learning models only have to fit relatively simple, low-dimensional, highly structured subspaces within their potential input space (latent manifolds). Within one of these manifolds, it's always possible to interpolate between two inputs, that is to say, morph one into another via a continuous path along which all points fall on the manifold. The ability to interpolate between samples is the key to generalization in deep learning. == The information geometry of statistical manifolds == An empirically-motivated approach to the manifold hypothesis focuses on its correspondence with an effective theory for manifold learning under the assumption that robust machine learning requires encoding the dataset of interest using methods for data compression. This perspective gradually emerged using the tools of information geometry thanks to the coordinated effort of scientists working on the efficient coding hypothesis, predictive coding and variational Bayesian methods. The argument for reasoning about the information geometry on the latent space of distributions rests upon the existence and uniqueness of the Fisher information metric. In this general setting, we are trying to find a stochastic embedding of a statistical manifold. From the perspective of dynamical systems, in the big data regime this manifold generally exhibits certain properties such as homeostasis: We can sample large amounts of data from the underlying generative process. Machine Learning experiments are reproducible, so the statistics of the generating process exhibit stationarity. In a sense made precise by theoretical neuroscientists working on the free energy principle, the statistical manifold in question possesses a Markov blanket.

  Read more →
• 

  Lexical choice

  Lexical choice is the subtask of Natural language generation that involves choosing the content words (nouns, non-auxiliary verbs, adjectives, and adverbs) in a generated text. Function words (determiners, for example) are usually chosen during realisation. == Examples == The simplest type of lexical choice involves mapping a domain concept (perhaps represented in an ontology) to a word. For example, the concept Finger might be mapped to the word finger. A more complex situation is when a domain concept is expressed using different words in different situations. For example, the domain concept Value-Change can be expressed in many ways: The temperature rose: the verb rose is used for a Value-Change in temperature which increases the value. The temperature fell: the verb fell is used for a Value-Change in temperature which decreases the value. The rain got heavier: the phrase got heavier is used for a Value-Change in precipitation amount when the precipitation is rain. Sometimes words can communicate additional contextual information, for example: The temperature plummeted: the verb plummeted is used for a Value-Change in temperature which decreases the value, when the change is rapid and large. Contextual information is especially significant for vague terms such as tall. For example, a 2m tall man is tall, but a 2m tall horse is small. == Linguistic perspective == Lexical choice modules must be informed by linguistic knowledge of how the system's input data maps onto words. This is a question of semantics, but it is also influenced by syntactic factors (such as collocation effects) and pragmatic factors (such as context). Hence NLG systems need linguistic models of how meaning is mapped to words in the target domain (genre) of the NLG system. Genre tends to be very important; for example the verb veer has a very specific meaning in weather forecasts (wind direction is changing in a clockwise direction) which it does not have in general English, and a weather-forecast generator must be aware of this genre-specific meaning. In some cases there are major differences in how different people use the same word; for example, some people use by evening to mean 6PM and others use it to mean midnight. Psycholinguists have shown that when people speak to each other, they agree on a common interpretation via lexical alignment; this is not something which NLG systems can yet do. Ultimately, lexical choice must deal with the fundamental issue of how language relates to the non-linguistic world. For example, a system which chose colour terms such as red to describe objects in a digital image would need to know which RGB pixel values could generally be described as red; how this was influenced by visual (lighting, other objects in the scene) and linguistic (other objects being discussed) context; what pragmatic connotations were associated with red (for example, when an apple is called red, it is assumed to be ripe as well as have the colour red); and so forth. == Algorithms and models == A number of algorithms and models have been developed for lexical choice in the research community, for example Edmonds developed a model for choosing between near-synonyms (words with similar core meanings but different connotations). However such algorithms and models have not been widely used in applied NLG systems; such systems have instead often used quite simple computational models, and invested development effort in linguistic analysis instead of algorithm development.

  Read more →
• 

  Leakage (machine learning)

  In statistics and machine learning, leakage (also known as data leakage or target leakage) refers to the use of information during model training that would not be available at prediction time. This results in overly optimistic performance estimates, as the model appears to perform better during evaluation than it actually would in a production environment. Leakage is often subtle and indirect, making it difficult to detect and eliminate. It can lead a statistician or modeler to select a suboptimal model, which may be outperformed by a leakage-free alternative. == Leakage modes == Leakage can occur at multiple stages of the machine learning workflow. Broadly, its sources can be divided into two categories: those arising from features and those arising from training examples. === Feature leakage === Feature or column-wise leakage is caused by the inclusion of columns which are one of the following: a duplicate label, a proxy for the label, or the label itself. These features, known as anachronisms, will not be available when the model is used for predictions, and result in leakage if included when the model is trained. For example, including a "MonthlySalary" column when predicting "YearlySalary"; or "MinutesLate" when predicting "IsLate". === Training example leakage === Row-wise leakage is caused by improper sharing of information between rows of data. Types of row-wise leakage include: Premature featurization; leaking from premature featurization before Cross-validation/Train/Test split (must fit MinMax/ngrams/etc on only the train split, then transform the test set) Duplicate rows between train/validation/test (for example, oversampling a dataset to pad its size before splitting; or, different rotations/augmentations of a single image; bootstrap sampling before splitting; or duplicating rows to up sample the minority class) Non-independent and identically distributed random (non-IID) data Time leakage (for example, splitting a time-series dataset randomly instead of newer data in test set using a train/test split or rolling-origin cross-validation) Group leakage—not including a grouping split column (for example, Andrew Ng's group had 100k x-rays of 30k patients, meaning ~3 images per patient. The paper used random splitting instead of ensuring that all images of a patient were in the same split. Hence the model partially memorized the patients instead of learning to recognize pneumonia in chest x-rays.) A 2023 review found data leakage to be "a widespread failure mode in machine-learning (ML)-based science", having affected at least 294 academic publications across 17 disciplines, and causing a potential reproducibility crisis. == Detection == Data leakage in machine learning can be detected through various methods, focusing on performance analysis, feature examination, data auditing, and model behavior analysis. Performance-wise, unusually high accuracy or significant discrepancies between training and test results often indicate leakage. Inconsistent cross-validation outcomes may also signal issues. Feature examination involves scrutinizing feature importance rankings and ensuring temporal integrity in time series data. A thorough audit of the data pipeline is crucial, reviewing pre-processing steps, feature engineering, and data splitting processes. Detecting duplicate entries across dataset splits is also important. For language models, the Min-K% method can detect the presence of data in a pretraining dataset. It presents a sentence suspected to be present in the pretraining dataset, and computes the log-likelihood of each token, then compute the average of the lowest K of these. If this exceeds a threshold, then the sentence is likely present. This method is improved by comparing against a baseline of the mean and variance. Analyzing model behavior can reveal leakage. Models relying heavily on counter-intuitive features or showing unexpected prediction patterns warrant investigation. Performance degradation over time when tested on new data may suggest earlier inflated metrics due to leakage. Advanced techniques include backward feature elimination, where suspicious features are temporarily removed to observe performance changes. Using a separate hold-out dataset for final validation before deployment is advisable.

  Read more →
• 

  Multi-armed bandit

  In probability theory and machine learning, the multi-armed bandit problem (sometimes called the K- or N-armed bandit problem) is named from imagining a gambler at a row of slot machines (sometimes known as "one-armed bandits"), who has to decide which machines to play, how many times to play each machine and in which order to play them, and whether to continue with the current machine or try a different machine. More generally, it is a problem in which a decision maker iteratively selects one of multiple fixed choices (i.e., arms or actions) when the properties of each choice are only partially known at the time of allocation, and may become better understood as time passes. A fundamental aspect of bandit problems is that choosing an arm does not affect the properties of the arm or other arms. Instances of the multi-armed bandit problem include the task of iteratively allocating a fixed, limited set of resources between competing (alternative) choices in a way that minimizes the regret. A notable alternative setup for the multi-armed bandit problem includes the "best arm identification (BAI)" problem where the goal is instead to identify the best choice by the end of a finite number of rounds. The multi-armed bandit problem is a classic reinforcement learning problem that exemplifies the exploration–exploitation tradeoff dilemma. In contrast to general reinforcement learning, the selected actions in bandit problems do not affect the reward distribution of the arms. The multi-armed bandit problem also falls into the broad category of stochastic scheduling. In the problem, each machine provides a random reward from a probability distribution specific to that machine, that is not known a priori. The objective of the gambler is to maximize the sum of rewards earned through a sequence of lever pulls. The crucial tradeoff the gambler faces at each trial is between "exploitation" of the machine that has the highest expected payoff and "exploration" to get more information about the expected payoffs of the other machines. The trade-off between exploration and exploitation is also faced in machine learning. In practice, multi-armed bandits have been used to model problems such as managing research projects in a large organization, like a science foundation or a pharmaceutical company. In early versions of the problem, the gambler begins with no initial knowledge about the machines. Herbert Robbins in 1952, realizing the importance of the problem, constructed convergent population selection strategies in "some aspects of the sequential design of experiments". A theorem, the Gittins index, first published by John C. Gittins, gives an optimal policy for maximizing the expected discounted reward. == Empirical motivation == The multi-armed bandit problem models an agent that simultaneously attempts to acquire new knowledge (called "exploration") and optimize their decisions based on existing knowledge (called "exploitation"). The agent attempts to balance these competing tasks in order to maximize their total value over the period of time considered. There are many practical applications of the bandit model, for example: clinical trials investigating the effects of different experimental treatments while minimizing patient losses, adaptive routing efforts for minimizing delays in a network, financial portfolio design In these practical examples, the problem requires balancing reward maximization based on the knowledge already acquired with attempting new actions to further increase knowledge. This is known as the exploitation vs. exploration tradeoff in machine learning. The model has also been used to control dynamic allocation of resources to different projects, answering the question of which project to work on, given uncertainty about the difficulty and payoff of each possibility. Originally considered by Allied scientists in World War II, it proved so intractable that, according to Peter Whittle, the problem was proposed to be dropped over Germany so that German scientists could also waste their time on it. The version of the problem now commonly analyzed was formulated by Herbert Robbins in 1952. == The multi-armed bandit model == The multi-armed bandit (short: bandit or MAB) can be seen as a set of real distributions B = { R 1 , … , R K } {\displaystyle B=\{R_{1},\dots ,R_{K}\}} , each distribution being associated with the rewards delivered by one of the K ∈ N + {\displaystyle K\in \mathbb {N} ^{+}} levers. Let μ 1 , … , μ K {\displaystyle \mu _{1},\dots ,\mu _{K}} be the mean values associated with these reward distributions. The gambler iteratively plays one lever per round and observes the associated reward. The objective is to maximize the sum of the collected rewards. The horizon H {\displaystyle H} is the number of rounds that remain to be played. The bandit problem is formally equivalent to a one-state Markov decision process. The regret ρ {\displaystyle \rho } after T {\displaystyle T} rounds is defined as the expected difference between the reward sum associated with an optimal strategy and the sum of the collected rewards: ρ = T μ ∗ − ∑ t = 1 T r ^ t {\displaystyle \rho =T\mu ^{}-\sum _{t=1}^{T}{\widehat {r}}_{t}} , where μ ∗ {\displaystyle \mu ^{}} is the maximal reward mean, μ ∗ = max k { μ k } {\displaystyle \mu ^{}=\max _{k}\{\mu _{k}\}} , and r ^ t {\displaystyle {\widehat {r}}_{t}} is the reward in round t {\displaystyle t} . A zero-regret strategy is a strategy whose average regret per round ρ / T {\displaystyle \rho /T} tends to zero with probability 1 when the number of played rounds tends to infinity. Intuitively, zero-regret strategies are guaranteed to converge to a (not necessarily unique) optimal strategy if enough rounds are played. == Variations == A common formulation is the Binary multi-armed bandit or Bernoulli multi-armed bandit, which issues a reward of one with probability p {\displaystyle p} , and otherwise a reward of zero. Another formulation of the multi-armed bandit has each arm representing an independent Markov machine. Each time a particular arm is played, the state of that machine advances to a new one, chosen according to the Markov state evolution probabilities. There is a reward depending on the current state of the machine. In a generalization called the "restless bandit problem", the states of non-played arms can also evolve over time. There has also been discussion of systems where the number of choices (about which arm to play) increases over time. Computer science researchers have studied multi-armed bandits under worst-case assumptions, obtaining algorithms to minimize regret in both finite and infinite (asymptotic) time horizons for both stochastic and non-stochastic arm payoffs. === Best arm identification === An important variation of the classical regret minimization problem in multi-armed bandits is best arm identification (BAI), also known as pure exploration. This problem is crucial in various applications, including clinical trials, adaptive routing, recommendation systems, and A/B testing. In BAI, the objective is to identify the arm having the highest expected reward. An algorithm in this setting is characterized by a sampling rule, a decision rule, and a stopping rule, described as follows: Sampling rule: ( a t ) t ≥ 1 {\displaystyle (a_{t})_{t\geq 1}} is a sequence of actions at each time step Stopping rule: τ {\displaystyle \tau } is a (random) stopping time which suggests when to stop collecting samples Decision rule: a ^ τ {\displaystyle {\hat {a}}_{\tau }} is a guess on the best arm based on the data collected up to time τ {\displaystyle \tau } There are two predominant settings in BAI: Fixed budget setting: Given a time horizon T ≥ 1 {\displaystyle T\geq 1} , the objective is to identify the arm with the highest expected reward a ⋆ ∈ arg ⁡ max k μ k {\displaystyle a^{\star }\in \arg \max _{k}\mu _{k}} minimizing probability of error δ {\displaystyle \delta } . Fixed confidence setting: Given a confidence level δ ∈ ( 0 , 1 ) {\displaystyle \delta \in (0,1)} , the objective is to identify the arm with the highest expected reward a ⋆ ∈ arg ⁡ max k μ k {\displaystyle a^{\star }\in \arg \max _{k}\mu _{k}} with the least possible amount of trials and with probability of error P ( a ^ τ ≠ a ⋆ ) ≤ δ {\displaystyle \mathbb {P} ({\hat {a}}_{\tau }\neq a^{\star })\leq \delta } . For example using a decision rule, we could use m 1 {\displaystyle m_{1}} where m {\displaystyle m} is the machine no.1 (you can use a different variable respectively) and 1 {\displaystyle 1} is the amount for each time an attempt is made at pulling the lever, where ∫ ∑ m 1 , m 2 , ( . . . ) = M {\displaystyle \int \sum m_{1},m_{2},(...)=M} , identify M {\displaystyle M} as the sum of each attempts m 1 + m 2 {\displaystyle m_{1}+m_{2}} , (...) as needed, and from there you can get a ratio, sum or mean as quantitative probability and sample your formulation for each slots. You can also do ∫ ∑ k ∝ i N − (

  Read more →