Search results for " Machine Learning"

showing 10 items of 300 documents

On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operators

2020

The Tsetlin Machine (TM) is a recent machine learning algorithm with several distinct properties, such as interpretability, simplicity, and hardware-friendliness. Although numerous empirical evaluations report on its performance, the mathematical analysis of its convergence is still open. In this article, we analyze the convergence of the TM with only one clause involved for classification. More specifically, we examine two basic logical operators, namely, the "IDENTITY"- and "NOT" operators. Our analysis reveals that the TM, with just one clause, can converge correctly to the intended logical operator, learning from training data over an infinite time horizon. Besides, it can capture arbit…

FOS: Computer and information sciencesComputer Science - Machine LearningTraining setLearning automataComputer Science - Artificial IntelligenceComputer sciencebusiness.industryApplied MathematicsTime horizonPropositional calculusLogical connectiveMachine Learning (cs.LG)Artificial Intelligence (cs.AI)Operator (computer programming)Computational Theory and MathematicsArtificial IntelligencePattern recognition (psychology)Convergence (routing)Identity (object-oriented programming)Computer Vision and Pattern RecognitionArtificial intelligencebusinessSoftwareInterpretabilityIEEE Transactions on Pattern Analysis and Machine Intelligence
researchProduct

Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise

2022

Authors accepted manuscript Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Q-learning is one of the most well-known Reinforcement Learning algorithms. There have been tremendous efforts to develop this algorithm using neural networks. Bootstrapped Deep Q-Learning Network is amongst them. It utilizes multiple neural network heads to introduce diversity into Q-learning. Dive…

FOS: Computer and information sciencesComputer Science - Machine LearningVDP::Teknologi: 500Artificial Intelligence (cs.AI)Artificial IntelligenceControl and Systems EngineeringComputer Science - Artificial IntelligenceElectrical and Electronic EngineeringSoftwareMachine Learning (cs.LG)
researchProduct

PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance

2019

Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was usually taken from the human visual perceptual system and how the system processes different perturbations in order to replicate to what extent it determines our ability to judge image quality. While recent works have presented deep neural networks trained to predict human perceptual quality, very few borrow any intuitions from the human visual system. To address this, we present PerceptNet, a convolutional neural network where the architecture has been chosen to reflect the structure and various stages in the human…

FOS: Computer and information sciencesComputer Science - Machine LearningVisual perceptionComputer scienceImage qualitymedia_common.quotation_subjectFeature extractionMachine Learning (stat.ML)02 engineering and technology01 natural sciencesConvolutional neural networkhuman visual systemMachine Learning (cs.LG)010309 opticsStatistics - Machine LearningPerception0103 physical sciences0202 electrical engineering electronic engineering information engineeringFOS: Electrical engineering electronic engineering information engineeringperceptual distancemedia_commonArtificial neural networkbusiness.industryDeep learningImage and Video Processing (eess.IV)Pattern recognitionElectrical Engineering and Systems Science - Image and Video Processingneural networksHuman visual system model020201 artificial intelligence & image processingArtificial intelligencebusiness
researchProduct

Extracting Deformation-Aware Local Features by Learning to Deform

2021

Despite the advances in extracting local features achieved by handcrafted and learning-based descriptors, they are still limited by the lack of invariance to non-rigid transformations. In this paper, we present a new approach to compute features from still images that are robust to non-rigid deformations to circumvent the problem of matching deformable surfaces and objects. Our deformation-aware local descriptor, named DEAL, leverages a polar sampling and a spatial transformer warping to provide invariance to rotation, scale, and image deformations. We train the model architecture end-to-end by applying isometric non-rigid deformations to objects in a simulated environment as guidance to pr…

FOS: Computer and information sciencesComputer Science - Machine Learning[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Computer Vision and Pattern Recognition (cs.CV)Computer Science::Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputer Science - Computer Vision and Pattern Recognition[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Machine Learning (cs.LG)ComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Implicit differentiation of Lasso-type models for hyperparameter optimization

2020

International audience; Setting regularization parameters for Lasso-type estimators is notoriously difficult, though crucial in practice. The most popular hyperparam-eter optimization approach is grid-search using held-out validation data. Grid-search however requires to choose a predefined grid for each parameter , which scales exponentially in the number of parameters. Another approach is to cast hyperparameter optimization as a bi-level optimization problem, one can solve by gradient descent. The key challenge for these methods is the estimation of the gradient w.r.t. the hyperpa-rameters. Computing this gradient via forward or backward automatic differentiation is possible yet usually s…

FOS: Computer and information sciencesComputer Science - Machine Learning[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]Statistics - Machine LearningMachine Learning (stat.ML)[STAT.ML] Statistics [stat]/Machine Learning [stat.ML]Machine Learning (cs.LG)
researchProduct

On the Universality of Graph Neural Networks on Large Random Graphs

2021

International audience; We study the approximation power of Graph Neural Networks (GNNs) on latent position random graphs. In the large graph limit, GNNs are known to converge to certain "continuous" models known as c-GNNs, which directly enables a study of their approximation power on random graph models. In the absence of input node features however, just as GNNs are limited by the Weisfeiler-Lehman isomorphism test, c-GNNs will be severely limited on simple random graph models. For instance, they will fail to distinguish the communities of a well-separated Stochastic Block Model (SBM) with constant degree function. Thus, we consider recently proposed architectures that augment GNNs with …

FOS: Computer and information sciencesComputer Science - Machine Learning[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]Statistics - Machine Learning[MATH.MATH-ST]Mathematics [math]/Statistics [math.ST]Machine Learning (stat.ML)[MATH.MATH-ST] Mathematics [math]/Statistics [math.ST][STAT.ML] Statistics [stat]/Machine Learning [stat.ML]Machine Learning (cs.LG)
researchProduct

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs

2020

International audience; We study properties of Graph Convolutional Networks (GCNs) by analyzing their behavior on standard models of random graphs, where nodes are represented by random latent variables and edges are drawn according to a similarity kernel. This allows us to overcome the difficulties of dealing with discrete notions such as isomorphisms on very large graphs, by considering instead more natural geometric aspects. We first study the convergence of GCNs to their continuous counterpart as the number of nodes grows. Our results are fully non-asymptotic and are valid for relatively sparse graphs with an average degree that grows logarithmically with the number of nodes. We then an…

FOS: Computer and information sciencesComputer Science - Machine Learning[STAT.ML]Statistics [stat]/Machine Learning [stat.ML][INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]Statistics - Machine LearningMachine Learning (stat.ML)[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG][STAT.ML] Statistics [stat]/Machine Learning [stat.ML]Machine Learning (cs.LG)
researchProduct

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games

2018

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to the vast capabilities of convolutional neural networks, that can extract useful features from noisy and complex data. Games are excellent tools to test and push the boundaries of novel RL algorithms because they give valuable insight into how well an algorithm can perform in isolated environments without the real-life consequences. Real-time strategy games (RTS) is a genre that has tremendous complexity and challenges the player in short and long-term planning. The…

FOS: Computer and information sciencesComputer Science - Machine Learningbusiness.industryComputer scienceComputer Science - Artificial IntelligenceComputingMilieux_PERSONALCOMPUTING02 engineering and technologyConvolutional neural networkAccelerated learningMachine Learning (cs.LG)03 medical and health sciences0302 clinical medicineArtificial Intelligence (cs.AI)Real-time strategy0202 electrical engineering electronic engineering information engineeringReinforcement learning020201 artificial intelligence & image processingArtificial intelligencebusiness030217 neurology & neurosurgery
researchProduct

Deep Non-Line-of-Sight Reconstruction

2020

The recent years have seen a surge of interest in methods for imaging beyond the direct line of sight. The most prominent techniques rely on time-resolved optical impulse responses, obtained by illuminating a diffuse wall with an ultrashort light pulse and observing multi-bounce indirect reflections with an ultrafast time-resolved imager. Reconstruction of geometry from such data, however, is a complex non-linear inverse problem that comes with substantial computational demands. In this paper, we employ convolutional feed-forward networks for solving the reconstruction problem efficiently while maintaining good reconstruction quality. Specifically, we devise a tailored autoencoder architect…

FOS: Computer and information sciencesComputer Science - Machine Learningbusiness.industryComputer scienceComputer Vision and Pattern Recognition (cs.CV)Image and Video Processing (eess.IV)Computer Science - Computer Vision and Pattern RecognitionNonlinear optics020207 software engineering02 engineering and technologyIterative reconstructionInverse problemElectrical Engineering and Systems Science - Image and Video ProcessingAutoencoderRendering (computer graphics)Machine Learning (cs.LG)Non-line-of-sight propagation0202 electrical engineering electronic engineering information engineeringFOS: Electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionArtificial intelligencebusiness
researchProduct

Dual Extrapolation for Sparse Generalized Linear Models

2020

International audience; Generalized Linear Models (GLM) form a wide class of regression and classification models, where prediction is a function of a linear combination of the input variables. For statistical inference in high dimension, sparsity inducing regularizations have proven to be useful while offering statistical guarantees. However, solving the resulting optimization problems can be challenging: even for popular iterative algorithms such as coordinate descent, one needs to loop over a large number of variables. To mitigate this, techniques known as screening rules and working sets diminish the size of the optimization problem at hand, either by progressively removing variables, o…

FOS: Computer and information sciencesComputer Science - Machine Learningextrapolation[MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC]Machine Learning (stat.ML)working setsgeneralized linear models[STAT.ML] Statistics [stat]/Machine Learning [stat.ML]Convex optimizationscreening rulesMachine Learning (cs.LG)[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]Statistics - Machine Learning[MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC]Lassosparse logistic regression
researchProduct