Document mosaicing is a process that stitches multiple, overlapping snapshot images of a document together to produce one large, high resolution composite. The document is slid under a stationary, over-the-desk camera by hand until all parts of the document are snapshotted by the camera's field of view. As the document slid under the camera, all motion of the document is coarsely tracked by the vision system. The document is periodically snapshotted such that the successive snapshots are overlap by about 50%. The system then finds the overlapped pairs and stitches them together repeatedly until all pairs are stitched together as one piece of document. The document mosaicing can be divided into four main processes. Tracking Feature detecting Correspondences establishing Images mosaicing. == Tracking (simple correlation process) == In this process, the motion of the document slid under the camera is coarsely tracked by the system. Tracking is performed by a process called simple correlation process. In the first frame of snapshots, a small patch is extracted from the center of the image as a correlation template. The correlation process is performed in the four times size of the patch area of the next frame. The motion of the paper is indicated by the peak in the correlation function. The peak in the correlation function indicates the motion of the paper. The template is resampled from this frame and the tracking continues until the template reaches the edge of the document. After the template reaches the edge of the document, another snapshot is taken and the tracking process performs repeatedly until the whole document is imaged. The snapshots are stored in an ordered list to facilitate pairing the overlapped images in later processes. == Feature detecting for efficient matching == Feature detection is the process of finding the transformation that aligns one image with another. There are two main approaches for feature detection. Feature-based approach : Motion parameters are estimated from point correspondences. This approach is suitable for the case that there is plenty supply of stable and detectable features. Featureless approach : When the motion between the two images is small, the motion parameters are estimated using optical flow. On the other hand, when the motion between the two images is large, the motion parameters are estimated using generalised cross-correlation. However, this approach requires a computationally expensive resources. Each image is segmented into a hierarchy of columns, lines, and words to match the organised sets of features across images. Skew angle estimation and columns, lines and words finding are the examples of feature detection operations. === Skew angle estimation === Firstly, the angle that the rows of text make with the image raster lines (skew angle) is estimated. It is assumed to lie in the range of ±20°. A small patch of text in the image is selected randomly and then rotated in the range of ±20° until the variance of the pixel intensities of the patch summed along the raster lines is maximised. To ensure that the found skew angle is accurate, the document mosaic system performs calculation at many image patches and derive the final estimation by finding the average of the individual angles weighted by the variance of the pixel intensities of each patch. === Columns, lines and words finding === In this operation, the de-skewed document is intuitively segmented into a hierarchy of columns, lines and words. The sensitivity to illumination and page coloration of the de-skewed document can be removed by applying a Sobel operator to the de-skewed image and thresholding the output to obtain the binary gradient, de-skewed image. The operation can be roughly separated into 3 steps: column segmentation, line segmentation and word segmentation. Columns are easily segmented from the binary gradient, de-skewed images by summing pixels vertically. Baselines of each row are segmented in the same way as the column segmentation process but horizontally. Finally, individual words are segmented by applying the vertical process at each segmented row. These segmentations are important because the document mosaic is created by matching the lower right corners of words in overlapping images pair. Moreover, the segmentation operation can organize the list of images in the context of a hierarchy of rows and column reliably. The segmentation operation involves a considerable amount of summing in the binary gradient, de-skewed images, which done by construct a matrix of partial sums whose elements are given by p i y = ∑ u = 1 i ∑ v = 1 j b u v {\displaystyle p_{iy}=\sum _{u=1}^{i}\sum _{v=1}^{j}b_{uv}} The matrix of partial sums is calculated in one pass through the binary gradient, de-skewed image. ∑ u = u 1 u 2 ∑ v = v 1 v 2 b u v = p u 2 v 2 + p u 1 v 1 − p u 1 v 2 − p u 2 v 1 {\displaystyle \sum _{u=u_{1}}^{u_{2}}\sum _{v=v_{1}}^{v_{2}}b_{uv}=p_{u_{2}v_{2}}+p_{u_{1}v_{1}}-p_{u_{1}v_{2}}-p_{u_{2}v_{1}}} == Correspondences establishing == The two images are now organized in hierarchy of linked lists in following structure : image=list of columns row=list of words column=list of row word=length (in pixels) At the bottom of the structure, the length of each word is recorded for establishing correspondence between two images to reduce to search only the corresponding structures for the groups of words with the matching lengths. === Seed match finding === A seed match finding is done by comparing each row in image1 with each row in image2. The two rows are then compared to each other by every word. If the length (in pixel) of the two words (one from image1 and one from image2) and their immediate neighbours agree with each other within a predefined tolerance threshold (5 pixels, for example), then they are assumed to match. The row of each image is assumed a match if there are three or more word matches between the two rows. The seed match finding operation is terminated when two pairs of consecutive row match are found. === Match list building === After finishing a seed match finding operation, the next process is to build the match list to generate the correspondences points of the two images. The process is done by searching the matching pairs of rows away from the seed row. == Images mosaicing == Given the list of corresponding points of the two images, finding the transformation of the overlapping portion of the images is the next process. Assuming a pinhole camera model, the transformation between pixels (u,v) of image 1 and pixels (u0, v0) of image 2 is demonstrated by a plane-to-plane projectivity. [ s u ′ s v ′ s ] = [ p 11 p 12 p 13 p 21 p 22 p 23 p 31 p 32 1 ] [ u v 1 ] E q .1 {\displaystyle \left[{\begin{array}{c}su'\\sv'\\s\end{array}}\right]=\left[{\begin{array}{ccc}p_{11}&p_{12}&p_{13}\\p_{21}&p_{22}&p_{23}\\p_{31}&p_{32}&1\end{array}}\right]\left[{\begin{array}{c}u\\v\\1\end{array}}\right]\qquad Eq.1} The parameters of the projectivity is found from four pairs of matching points. RANSAC regression technique is used to reject outlying matches and estimate the projectivity from the remaining good matches. The projectivity is fine-tuned using correlation at the corners of the overlapping portion to obtain four correspondences to sub-pixel accuracy. Therefore, image1 is then transformed into image2's coordinate system using Eq.1. The typical result of the process is shown in Figure 5. === Many images coping === Finally, the whole page composition is built up by mapping all the images into the coordinate system of an "anchor" image, which is normally the one nearest the page center. The transformations to the anchor frame are calculated by concatenating the pair-wise transformations found earlier. The raw document mosaic is shown in Figure 6. However, there might be a problem of non-consecutive images that are overlap. This problem can be solved by performing Hierarchical sub-mosaics. As shown in Figure 7, image1 and image2 are registered, as are image3 and image4, creating two sub-mosaics. These two sub-mosaics are later stitched together in another mosaicing process. == Applied areas == There are various areas that the technique of document mosaicing can be applied to such as : Text segmentation of images of documents Document Recognition Interaction with paper on the digital desk Video mosaics for virtual environments Image registration techniques == Relevant research papers == Huang, T.S.; Netravali, A.N. (1994). "Motion and structure from feature correspondences: A review". Proceedings of the IEEE. 82 (2): 252–268. doi:10.1109/5.265351. D.G. Lowe. [1] Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Boston, 1985. Irani, M.; Peleg, S. (1991). "Improving resolution by image registration". CVGIP: Graphical Models and Image Processing. 53 (3): 231–239. doi:10.1016/1049-9652(91)90045-L. S2CID 4834546. Shivakumara, P.; Kumar, G. Hemantha; Guru, D. S.; Nagabhushan, P. (2006). "
StatMuse
StatMuse Inc. is an American artificial intelligence company founded in 2014. It operates an eponymous website that hosts a database of sports statistics covering the four major North American sports leagues, the Women's National Basketball Association (WNBA), NCAA Division I men's basketball, NCAA Division I Football Bowl Subdivision, the Big Five association football leagues in Europe, and various professional golf tours. == History == The company was founded by friends Adam Elmore and Eli Dawson in 2014. In email correspondence to the Springfield News-Leader, Elmore detailed that he and Dawson, fans of the National Basketball Association (NBA), were compelled to create StatMuse after they realized there was no online platform where they could search "Lebron James most points" [sic] and quickly get a result "showing his highest scoring games." As a startup, the company's goal was to utilize a type of artificial intelligence called natural language processing (NLP) for sports. In 2015, the company was part of the second group of startups accepted into the Disney Accelerator program. The company secured support from several investors, including The Walt Disney Company, Techstars, Allen & Company, the NFL Players Association, Greycroft and NBA Commissioner David Stern. As part of their partnership with Disney, StatMuse signed a content deal with ESPN (owned by Disney) to provide stats content on social media and television during the 2015–16 NBA season. Initially, the company only had stats available for the NBA, but eventually expanded to provide stats for the other major North American sports leagues. The company's initial demographic was players of fantasy sports, but it eventually expanded to target general sports fans as well. StatMuse offers responses to user queries in the voices of sports-related public figures. Dawson shared with VentureBeat that StatMuse brings people in and records them saying different words and phrases. These celebrity voices were made accessible through Google's Google Assistant service, Microsoft's Cortana virtual assistant, and Amazon's Echo devices. The company launched its phone app in September 2017. The app allows users to access StatMuse's sports statistics database by submitting queries in their natural language. Upon the launch of the phone app, Fitz Tepper of TechCrunch wrote that: "The technology isn't perfect – some of the pauses between words are a bit awkward, making it clear that some phrases are being stitched together on the fly. But this is the exception, and on the whole, most responses sound pretty good." StatMuse plug-ins for Slack and Facebook Messenger were also made, providing text-based sports stats. In 2019, StatMuse received investment from the Google Assistant Investment program. The service launched a premium option dubbed StatMuse+ in May 2023, offering options that had previously been included for free, such as unlimited searches and full results in data tables. The premium version also included early access to new features and a personalized search history, as well as not having ads. The app received a variety of feedback. In January 2024, the service launched a Premier League version of the website dubbed StatMuse FC. It is planned to introduce more leagues on the website.
Perceptual computing
Perceptual computing is an application of Zadeh's theory of computing with words on the field of assisting people to make subjective judgments. == Perceptual computer == The perceptual computer – Per-C – an instantiation of perceptual computing – has the architecture that is depicted in Fig. 1 [2]–[6]. It consists of three components: encoder, CWW engine and decoder. Perceptions – words – activate the Per-C and are the Per-C output (along with data); so, it is possible for a human to interact with the Per-C using just a vocabulary. A vocabulary is application (context) dependent, and must be large enough so that it lets the end-user interact with the Per-C in a user-friendly manner. The encoder transforms words into fuzzy sets (FSs) and leads to a codebook – words with their associated FS models. The outputs of the encoder activate a Computing With Words (CWW) engine, whose output is one or more other FSs, which are then mapped by the decoder into a recommendation (subjective judgment) with supporting data. The recommendation may be in the form of a word, group of similar words, rank or class. Although many details are needed in order to implement the Per-C's three components – encoder, decoder and CWW engine – and they are covered in [5], it is when the Per-C is applied to specific applications, that the focus on the methodology becomes clear. Stepping back from those details, the methodology of perceptual computing is: Focus on an application (A). Establish a vocabulary (or vocabularies) for A. Collect interval end-point data from a group of subjects (representative of the subjects who will use the Per-C) for all of the words in the vocabulary. Map the collected word data into word-FOUs by using the Interval Approach [1], [5, Ch. 3]. The result of doing this is the codebook (or codebooks) for A, and completes the design of the encoder of the Per-C. Choose an appropriate CWW engine for A. It will map IT2 FSs into one or more IT2 FSs. Examples of CWW engines are: IF-THEN rules [5, Ch. 6] and Linguistic Weighted Averages [6], [5, Ch. 5]. If an existing CWW engine is available for A, then use its available mathematics to compute its output(s). Otherwise, develop such mathematics for the new kind of CWW engine. The new CWW engine should be constrained so that its output(s) resemble the FOUs in the codebook(s) for A. Map the IT2 FS outputs from the CWW engine into a recommendation at the output of the decoder. If the recommendation is a word, rank or class, then use existing mathematics to accomplish this mapping [5, Ch. 4]. Otherwise, develop such mathematics for the new kind of decoder. == Applications of Per-C == To-date a Per-C has been implemented for the following four applications: (1) investment decision-making, (2) social judgment making, (3) distributed decision making, and (4) hierarchical and distributed decision-making. A specific example of the fourth application is the so-called Journal Publication Judgment Advisor [5, Ch. 10] in which for the first time only words are used at every level of the following hierarchical and distributed decision making process: n reviewers have to provide a subjective recommendation about a journal article that has been sent to them by the Associate Editor, who then has to aggregate the independent recommendations into a final recommendation that is sent to the Editor-in-Chief of the journal. Because it is very problematic to ask reviewers to provide numerical scores for paper-evaluation sub-categories (the two major categories are Technical Merit and Presentation), such as importance, content, depth, style, organization, clarity, references, etc., each reviewer will only be asked to provide a linguistic score for each of these categories. They will not be asked for an overall recommendation about the paper because in the past it is quite common for reviewers who provide the same numerical scores for such categories to give very different publishing recommendations. By leaving a specific recommendation to the associate editor such inconsistencies can hope to be eliminated. How words can be aggregated to reflect each reviewer's recommendation as well as the expertise of each reviewer about the paper's subject matter is done using a linguistic weighted average. Although the journal publication judgment advisor uses reviewers and an associate editor, the word “reviewer” could be replaced by judge, expert, low-level manager, commander, referee, etc., and the term “associate editor” could be replaced by control center, command center, higher-level manager, etc. So, this application has potential wide applicability to many other applications. Recently, a new Per-C based Failure mode and effects analysis (FMEA) methodology was developed, with its application to edible bird's nest farming, in Borneo, has been reported. In addition, application of Per-C based method to educational assessment, for cooperative learning of students has been reported. In summary, the Per-C (whose development has taken more than a decade) is the first complete implementation of Zadeh's CWW paradigm, as applied to assisting people to make subjective judgments.
Orange (software)
Orange is an open-source data visualization, machine learning and data mining toolkit. It features a visual programming front-end for exploratory qualitative data analysis and interactive data visualization. == Description == Orange is a component-based visual programming software package for data visualization, machine learning, data mining, and data analysis. Orange components are called widgets. They range from simple data visualization, subset selection, and preprocessing to empirical evaluation of learning algorithms and predictive modeling. Visual programming is implemented through an interface in which workflows are created by linking predefined or user-designed widgets, while advanced users can use Orange as a Python library for data manipulation and widget alteration. == Software == Orange is an open-source software package released under GPL and hosted on GitHub. Versions up to 3.0 include core components in C++ with wrappers in Python. From version 3.0 onwards, Orange uses common Python open-source libraries for scientific computing, such as numpy, scipy and scikit-learn, while its graphical user interface operates within the cross-platform Qt framework. The default installation includes a number of machine learning, preprocessing and data visualization algorithms in 6 widget sets (data, transform, visualize, model, evaluate and unsupervised). Additional functionalities are available as add-ons (text-mining, image analytics, bioinformatics, etc.). Orange is supported on macOS, Windows and Linux and can also be installed from the Python Package Index repository (pip install Orange3). == Features == Orange consists of a canvas interface onto which the user places widgets and creates a data analysis workflow. Widgets offer basic functionalities such as reading the data, showing a data table, selecting features, training predictors, comparing learning algorithms, visualizing data elements, etc. The user can interactively explore visualizations or feed the selected subset into other widgets. Canvas: graphical front-end for data analysis Widgets: Data: widgets for data input, data filtering, sampling, imputation, feature manipulation and feature selection Visualize: widgets for common visualization (box plot, histograms, scatter plot) and multivariate visualization (mosaic display, sieve diagram). Classify: a set of supervised machine learning algorithms for classification Regression: a set of supervised machine learning algorithms for regression Evaluate: cross-validation, sampling-based procedures, reliability estimation and scoring of prediction methods Unsupervised: unsupervised learning algorithms for clustering (k-means, hierarchical clustering) and data projection techniques (multidimensional scaling, principal component analysis, correspondence analysis). == Add-ons == Orange users can extend their core set of components with components in the add-ons. Supported add-ons include: Associate: components for mining frequent itemsets and association rule learning. Bioinformatics: components for gene expression analysis, enrichment, and access to expression databases (e.g., Gene Expression Omnibus) and pathway libraries. Data fusion: components for fusing different data sets, collective matrix factorization, and exploration of latent factors. Educational: components for teaching machine learning concepts, such as k-means clustering, polynomial regression, stochastic gradient descent, ... Explain: provides an extension with components for the model explanation, including Shapley value analysis Geo: components for working with geospatial data. Image analytics: components for working with images and ImageNet embeddings Network: components for graph and network analysis. Text mining: components for natural language processing and text mining. Time series: widget components for time series analysis and modeling. Single-cell: support for single-cell gene expression analysis, including components for loading single-cell data, filtering and batch effect removal, marker genes discovery, scoring of cells and genes, and cell type prediction. Spectroscopy: components for analyzing and visualization of (hyper)spectral datasets. Survival analysis: add-on for data analysis dealing with survival data. It includes widgets for standard survival analysis techniques, such as the Kaplan-Meier plot, the Cox regression model, and several derivative widgets. World Happiness: support for downloading socioeconomic data from a database, including OECD and World Development Indicators. Provides access to thousands of country indicators from various economic databases. Fairness: add-on for evaluation and creation of fair machine learning models without discrimination. Widgets range from computing fairness metrics like statistical parity to post-, pre-, in-processing methods to build fair models. == Objectives == The program provides a platform for experiment selection, recommendation systems, and predictive modelling and is used in biomedicine, bioinformatics, genomic research, and teaching. In science, it is used as a platform for testing new machine learning algorithms and for implementing new techniques in genetics and bioinformatics. In education, it was used for teaching machine learning and data mining methods to students of biology, biomedicine, and informatics. == Extensions == Various projects build on Orange either by extending the core components with add-ons or using only the Orange Canvas to exploit the implemented visual programming features and GUI. OASYS — ORange SYnchrotron Suite scOrange — single cell biostatistics Quasar — data analysis in natural sciences == History == In 1996, the University of Ljubljana and Jožef Stefan Institute started development of ML, a machine learning framework in C++, and Python bindings were developed for this framework in 1997, which, together with emerging Python modules, formed a joint framework called Orange. Over the following years, most contemporary major algorithms for data mining and machine learning were implemented in C++ (Orange's core) or Python modules. In 2002, first prototypes to create a flexible graphical user interface were designed using Pmw Python megawidgets. In 2003, the graphical user interface was redesigned and re-developed for Qt framework using PyQt Python bindings. The visual programming framework was defined, and the development of widgets (graphical components of the data analysis pipeline) began. In 2005, extensions for data analysis in bioinformatics was created. In 2008, Mac OS X DMG and Fink-based installation packages were developed. In 2009, over 100 widgets were created and maintained. In 2009, Orange 2.0 beta was released, offering installation packages on the website based on the daily compiling cycle. In 2012, a new object hierarchy was imposed, replacing the old module-based structure. In 2013, a significant redesign of the graphical user interface included a new toolbox and depiction of workflows. In 2015, Orange 3.0 was released. Orange stores the data in NumPy arrays; machine learning algorithms mostly use scikit-learn. In 2015, a text analysis add-on for Orange3 was released. In 2016, Orange released version 3.3. Development scheduled a monthly cycle for stable releases. In 2016, Orange began development and release of an Image Analytics add-on, with server-side deep neural networks for image embedding In 2017, a Spectroscopy add-on for the analysis of spectral data was introduced. In 2017, Geo, an add-on for dealing with geo-location data and visualisation of geo maps was introduced In 2018, Orange began development and release of an add-on for single-cell data analysis. In 2019, Orange separated its graphical interface for development as a separate project, orange-canvas-core In 2020, Orange introduced the Explain add-on with widgets for explaining classification models and regression models, highlighting the strength and contributions specific features make towards predicting a specific class. In 2022, World Happiness, an add-on for the Orange3 data mining suite, was introduced, providing widgets for accessing socioeconomic data from various databases such as World Happiness Report, World Development Indicators, OECD. In 2022, Orange extended the Explain add-on with an Individual Conditional Expectation plot and the Permutation Feature Importance technique. In 2023, Orange introduced the Fairness add-on, including widgets to calculate bias metrics, as well as widgets for pre-, post-, and in-processing methods, allowing the creation of models less susceptible to systematic error due to the vagaries of the data set.
Generative adversarial network
A generative adversarial network (GAN) is a class of machine learning frameworks and a prominent framework for approaching generative artificial intelligence. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014. In a GAN, two neural networks compete with each other in the form of a zero-sum game, where one agent's gain is another agent's loss. Given a training set, this technique learns to generate new data with the same statistics as the training set. For example, a GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers, having many realistic characteristics. Though originally proposed as a form of generative model for unsupervised learning, GANs have also proved useful for semi-supervised learning, fully supervised learning, and reinforcement learning. The core idea of a GAN is based on the "indirect" training through the discriminator, another neural network that can tell how "realistic" the input seems, which itself is also being updated dynamically. This means that the generator is not trained to minimize the distance to a specific image, but rather to fool the discriminator. This enables the model to learn in an unsupervised manner. GANs are similar to mimicry in evolutionary biology, with an evolutionary arms race between both networks. == Definition == === Mathematical === The original GAN is defined as the following game: Each probability space ( Ω , μ ref ) {\displaystyle (\Omega ,\mu _{\text{ref}})} defines a GAN game. There are 2 players: generator and discriminator. The generator's strategy set is P ( Ω ) {\displaystyle {\mathcal {P}}(\Omega )} , the set of all probability measures μ G {\displaystyle \mu _{G}} on Ω {\displaystyle \Omega } . The discriminator's strategy set is the set of Markov kernels μ D : Ω → P [ 0 , 1 ] {\displaystyle \mu _{D}:\Omega \to {\mathcal {P}}[0,1]} , where P [ 0 , 1 ] {\displaystyle {\mathcal {P}}[0,1]} is the set of probability measures on [ 0 , 1 ] {\displaystyle [0,1]} . The GAN game is a zero-sum game, with objective function L ( μ G , μ D ) := E x ∼ μ ref , y ∼ μ D ( x ) [ ln y ] + E x ∼ μ G , y ∼ μ D ( x ) [ ln ( 1 − y ) ] . {\displaystyle L(\mu _{G},\mu _{D}):=\operatorname {E} _{x\sim \mu _{\text{ref}},y\sim \mu _{D}(x)}[\ln y]+\operatorname {E} _{x\sim \mu _{G},y\sim \mu _{D}(x)}[\ln(1-y)].} The generator aims to minimize the objective, and the discriminator aims to maximize the objective. The generator's task is to approach μ G ≈ μ ref {\displaystyle \mu _{G}\approx \mu _{\text{ref}}} , that is, to match its own output distribution as closely as possible to the reference distribution. The discriminator's task is to output a value close to 1 when the input appears to be from the reference distribution, and to output a value close to 0 when the input looks like it came from the generator distribution. === In practice === The generative network generates candidates while the discriminative network evaluates them. This creates a contest based on data distributions, where the generator learns to map from a latent space to the true data distribution, aiming to produce candidates that the discriminator cannot distinguish from real data. The discriminator's goal is to correctly identify these candidates, but as the generator improves, its task becomes more challenging, increasing the discriminator's error rate. A known dataset serves as the initial training data for the discriminator. Training involves presenting it with samples from the training dataset until it achieves acceptable accuracy. The generator is trained based on whether it succeeds in fooling the discriminator. Typically, the generator is seeded with randomized input that is sampled from a predefined latent space (e.g. a multivariate normal distribution). Thereafter, candidates synthesized by the generator are evaluated by the discriminator. Independent backpropagation procedures are applied to both networks so that the generator produces better samples, while the discriminator becomes more skilled at flagging synthetic samples. When used for image generation, the generator is typically a deconvolutional neural network, and the discriminator is a convolutional neural network. === Relation to other statistical machine learning methods === GANs are implicit generative models, which means that they do not explicitly model the likelihood function nor provide a means for finding the latent variable corresponding to a given sample, unlike alternatives such as flow-based generative model. Compared to fully visible belief networks such as WaveNet and PixelRNN and autoregressive models in general, GANs can generate one complete sample in one pass, rather than multiple passes through the network. Compared to Boltzmann machines and linear ICA, there is no restriction on the type of function used by the network. Since neural networks are universal approximators, GANs are asymptotically consistent. Variational autoencoders might be universal approximators, but it is not proven as of 2017. == Mathematical properties == === Measure-theoretic considerations === This section provides some of the mathematical theory behind these methods. In modern probability theory based on measure theory, a probability space also needs to be equipped with a σ-algebra. As a result, a more rigorous definition of the GAN game would make the following changes:Each probability space ( Ω , B , μ ref ) {\displaystyle (\Omega ,{\mathcal {B}},\mu _{\text{ref}})} defines a GAN game. The generator's strategy set is P ( Ω , B ) {\displaystyle {\mathcal {P}}(\Omega ,{\mathcal {B}})} , the set of all probability measures μ G {\displaystyle \mu _{G}} on the measure-space ( Ω , B ) {\displaystyle (\Omega ,{\mathcal {B}})} . The discriminator's strategy set is the set of Markov kernels μ D : ( Ω , B ) → P ( [ 0 , 1 ] , B ( [ 0 , 1 ] ) ) {\displaystyle \mu _{D}:(\Omega ,{\mathcal {B}})\to {\mathcal {P}}([0,1],{\mathcal {B}}([0,1]))} , where B ( [ 0 , 1 ] ) {\displaystyle {\mathcal {B}}([0,1])} is the Borel σ-algebra on [ 0 , 1 ] {\displaystyle [0,1]} .Since issues of measurability never arise in practice, these will not concern us further. === Choice of the strategy set === In the most generic version of the GAN game described above, the strategy set for the discriminator contains all Markov kernels μ D : Ω → P [ 0 , 1 ] {\displaystyle \mu _{D}:\Omega \to {\mathcal {P}}[0,1]} , and the strategy set for the generator contains arbitrary probability distributions μ G {\displaystyle \mu _{G}} on Ω {\displaystyle \Omega } . However, as shown below, the optimal discriminator strategy against any μ G {\displaystyle \mu _{G}} is deterministic, so there is no loss of generality in restricting the discriminator's strategies to deterministic functions D : Ω → [ 0 , 1 ] {\displaystyle D:\Omega \to [0,1]} . In most applications, D {\displaystyle D} is a deep neural network function. As for the generator, while μ G {\displaystyle \mu _{G}} could theoretically be any computable probability distribution, in practice, it is usually implemented as a pushforward: μ G = μ Z ∘ G − 1 {\displaystyle \mu _{G}=\mu _{Z}\circ G^{-1}} . That is, start with a random variable z ∼ μ Z {\displaystyle z\sim \mu _{Z}} , where μ Z {\displaystyle \mu _{Z}} is a probability distribution that is easy to compute (such as the uniform distribution, or the Gaussian distribution), then define a function G : Ω Z → Ω {\displaystyle G:\Omega _{Z}\to \Omega } . Then the distribution μ G {\displaystyle \mu _{G}} is the distribution of G ( z ) {\displaystyle G(z)} . Consequently, the generator's strategy is usually defined as just G {\displaystyle G} , leaving z ∼ μ Z {\displaystyle z\sim \mu _{Z}} implicit. In this formalism, the GAN game objective is L ( G , D ) := E x ∼ μ ref [ ln D ( x ) ] + E z ∼ μ Z [ ln ( 1 − D ( G ( z ) ) ) ] . {\displaystyle L(G,D):=\operatorname {E} _{x\sim \mu _{\text{ref}}}[\ln D(x)]+\operatorname {E} _{z\sim \mu _{Z}}[\ln(1-D(G(z)))].} === Generative reparametrization === The GAN architecture has two main components. One is casting optimization into a game, of form min G max D L ( G , D ) {\displaystyle \min _{G}\max _{D}L(G,D)} , which is different from the usual kind of optimization, of form min θ L ( θ ) {\displaystyle \min _{\theta }L(\theta )} . The other is the decomposition of μ G {\displaystyle \mu _{G}} into μ Z ∘ G − 1 {\displaystyle \mu _{Z}\circ G^{-1}} , which can be understood as a reparametrization trick. To see its significance, one must compare GAN with previous methods for learning generative models, which were plagued with "intractable probabilistic computations that arise in maximum likelihood estimation and related strategies". At the same time, Kingma and Welling and Rezende et al. developed the same idea of reparametrization into a general stochastic backpropagation method. Among its first applications was the variational autoencoder. === Move order and st
Caspio
Caspio, Inc. is an American software company providing a low-code platform for building cloud-based business applications. Founded in 2000 by Frank Zamani, the company is headquartered in Sunnyvale, California, with operations in Poland, the Philippines, and Spain. Caspio’s platform allows organizations to create online database applications and workflow tools without extensive coding. == History == Caspio was founded by Frank Zamani in 2000. The company initially focused on simplifying custom cloud applications and reducing development time and cost as compared to traditional software development. Caspio released the first version of its platform, Caspio Bridge, in 2001. In 2014, Caspio released a HIPAA-Compliant Edition of its low-code application development platform. Caspio also released an EU General Data Protection Regulation (GDPR) Compliance Edition of its low-code application development platform in 2016. Caspio's second European Software Development Center opened in Kraków, Poland in 2017. In 2019, Forrester Research listed Caspio and three other platforms in its highest of four ranked tiers of twelve low-code platforms for business developers based on rankings of offerings and strategy at that time. Caspio also opened data centers in Montreal, Canada and India in 2020.
International Conference on Automated Planning and Scheduling
The International Conference on Automated Planning and Scheduling (ICAPS) is a leading international academic conference in automated planning and scheduling held annually for researchers and practitioners in planning and scheduling. ICAPS is supported by the National Science Foundation, the journal Artificial Intelligence, and other supporters. == The IPC and PDDL == ICAPS conducts the International Planning Competition (IPC), a competition scheduled every few years that empirically evaluates state-of-the-art planning systems on a collection of benchmark problems. The Planning Domain Definition Language (PDDL) was developed mainly to make the 1998/2000 International Planning Competition possible, and then evolved with each competition. PDDL is an attempt to standardize Artificial Intelligence (AI) planning languages. PDDL was first developed by Drew McDermott and his colleagues in 1998, inspired by STRIPS, ADL, and other sources. == History == The ICAPS conferences began in 2003 as a merge of two bi-annual conferences, the International Conference on Artificial Intelligence Planning and Scheduling (AIPS) and the European Conference on Planning (ECP). == List of events ==