Reducing the Dimensionality of Data with Neural Networks
From MaRDI portal
Publication:3101410
DOI10.1126/science.1127647zbMath1226.68083OpenAlexW2100495367WikidataQ31050179 ScholiaQ31050179MaRDI QIDQ3101410
Ruslan R. Salakhutdinov, Geoffrey E. Hinton
Publication date: 28 November 2011
Published in: Science (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/213d7af7107fa4921eb0adea82c9f711fd105232
Related Items
Research on three-step accelerated gradient algorithm in deep learning, Parametric UMAP Embeddings for Representation and Semisupervised Learning, Effects of depth, width, and initialization: A convergence analysis of layer-wise training for deep linear neural networks, Symplectic Model Reduction of Hamiltonian Systems on Nonlinear Manifolds and Approximation with Weakly Symplectic Autoencoder, Approximate and discrete Euclidean vector bundles, A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations, Mean-field inference methods for neural networks, Interpolating between boolean and extremely high noisy patterns through minimal dense associative memories, Legendre equivalences of spherical Boltzmann machines, Learning quantum structures in compact localized eigenstates, A Mixed Wavelet-Learning Method of Predicting Macroscopic Effective Heat Transfer Conductivities of Braided Composite Materials, Forward Stepwise Deep Autoencoder-Based Monotone Nonlinear Dimensionality Reduction Methods, Features Reweighting and Selection in ligand-based Virtual Screening for Molecular Similarity Searching Based on Deep Belief Networks, On the combination of kernel principal component analysis and neural networks for process indirect control, A Nonlinear Matrix Decomposition for Mining the Zeros of Sparse Data, RANDOM NEURAL NETWORK METHODS AND DEEP LEARNING, Learning probabilistic neural representations with randomly connected circuits, Unnamed Item, Unnamed Item, Unnamed Item, Justifying and Generalizing Contrastive Divergence, Learning the Dynamics of Objects by Optimal Functional Interpolation, Enhanced Gradient for Training Restricted Boltzmann Machines, Linearly Constrained Nonsmooth Optimization for Training Autoencoders, A converged deep graph semi-NMF algorithm for learning data representation, Koopman analysis of nonlinear systems with a neural network representation, Thermodynamics of bidirectional associative memories, Representations of hypergraph states with neural networks*, LSTM-based approach for predicting periodic motions of an impacting system via transient dynamics, A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training, Transfer-RLS method and transfer-FORCE learning for simple and fast training of reservoir computing models, Epicasting: an ensemble wavelet neural network for forecasting epidemics, Nonlinear reduced-order modeling for three-dimensional turbulent flow by large-scale machine learning, Estimating propensity scores using neural networks and traditional methods: a comparative simulation study, Probabilistic partition of unity networks for high‐dimensional regression problems, Statistical Inference, Learning and Models in Big Data, Discriminative group-sparsity constrained broad learning system for visual recognition, Predicting turbulent dynamics with the convolutional autoencoder echo state network, Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution, The emergence of a concept in shallow neural networks, Surrogate modeling for high dimensional uncertainty propagation via deep kernel polynomial chaos expansion, Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean, Multibody dynamics and control using machine learning, Fast convergence rates of deep neural networks for classification, Dynamics of a data-driven low-dimensional model of turbulent minimal Couette flow, Deep multimodal autoencoder for crack criticality assessment, Household financial health: a machine learning approach for data-driven diagnosis and prescription, Predicting circRNA-disease associations based on autoencoder and graph embedding, Non‐intrusive reduced‐order modeling using convolutional autoencoders, Physics-informed data-driven model for fluid flow in porous media, A taxonomy for similarity metrics between Markov decision processes, Airfoil-based convolutional autoencoder and long short-term memory neural network for predicting coherent structures evolution around an airfoil, Synthetic data generation: state of the art in health care domain, Unnamed Item, Unnamed Item, Recent Deep Learning Methods for Melanoma Detection: A Review, Applying neural network Poisson regression to predict cognitive score changes, Large Margin Low Rank Tensor Analysis, A Survey on Deep Learning for Multimodal Data Fusion, The Stochastic Delta Rule: Faster and More Accurate Deep Learning Through Adaptive Weight Noise, On Kernel Method–Based Connectionist Models and Supervised Deep Learning Without Backpropagation, Deep Learning with Dynamic Spiking Neurons and Fixed Feedback Weights, Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review, Convergence of Markovian stochastic approximation for Markov random fields with hidden variables, The structure of reconstructed flows in latent spaces, Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows, Open quantum generalisation of Hopfield neural networks, Decreasing the Size of the Restricted Boltzmann Machine, Semisupervised Deep Stacking Network with Adaptive Learning Rate Strategy for Motor Imagery EEG Recognition, Sparse identification of nonlinear dynamics with low-dimensionalized flow representations, Dynamics of Learning in MLP: Natural Gradient and Singularity Revisited, Statistics of Visual Responses to Image Object Stimuli from Primate AIT Neurons to DNN Neurons, Unnamed Item, Unnamed Item, Learning Binary Hash Codes for Large-Scale Image Search, Hierarchical model of natural images and the origin of scale invariance, Visual Recognition and Inference Using Dynamic Overcomplete Sparse Learning, Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning, Ensemble Kalman inversion: a derivative-free technique for machine learning tasks, Expansion of the effective action around non-Gaussian theories, Convolutional autoencoder and conditional random fields hybrid for predicting spatial-temporal chaos, Deep learning the holographic black hole with charge, DNN-PPI: A LARGE-SCALE PREDICTION OF PROTEIN–PROTEIN INTERACTIONS BASED ON DEEP NEURAL NETWORKS, SwitchNet: A Neural Network Model for Forward and Inverse Scattering Problems, Multilevel Artificial Neural Network Training for Spatially Correlated Learning, Nonlinear mode decomposition with convolutional neural networks for fluid dynamics, Unnamed Item, On the Achievability of Blind Source Separation for High-Dimensional Nonlinear Source Mixtures, Bucket renormalization for approximate inference, Learning Individualized Treatment Rules for Multiple-Domain Latent Outcomes, Enhancing performance of the back-propagation algorithm based on a novel regularization method of preserving inter-object-distance of data, Unnamed Item, Solving parametric PDE problems with artificial neural networks, Dynamical Variational Autoencoders: A Comprehensive Review, Nonlinear Level Set Learning for Function Approximation on Sparse Data with Applications to Parametric Differential Equations, Adaptive bridge control strategy for opinion evolution on social networks, A Tale of Two Bases: Local-Nonlocal Regularization on Image Patches with Convolution Framelets, Gaussian-spherical restricted Boltzmann machines, DeepSym: Deep Symbol Generation and Rule Learning for Planning from Unsupervised Robot Interaction, Low Rank Tensor Manifold Learning, Learning flexible sensori-motor mappings in a complex network, Cellular Automata for Efficient Image and Video Compression, Neighbourhood-preserving dimension reduction via localised multidimensional scaling, An Efficient Learning Procedure for Deep Boltzmann Machines, Learning Where to Attend with Deep Architectures for Image Tracking, Biological modelling of a computational spiking neural network with neuronal avalanches, Challenges for machine learning in RNA-protein interaction prediction, Autoencoders reloaded, Model order reduction for compressible flows solved using the discontinuous Galerkin methods, Autoencoder asset pricing models, A survey of deep network techniques all classifiers can adopt, How can we identify the sparsity structure pattern of high-dimensional data: an elementary statistical analysis to interpretable machine learning, A homotopy gated recurrent unit for predicting high dimensional hyperchaos, \(p\)-adic mathematical physics: the first 30 years, Deep relevant representation learning for soft sensing, Machine learning based data retrieval for inverse scattering problems with incomplete data, A survey of outlier detection in high dimensional data streams, Hierarchical semi-Markov conditional random fields for deep recursive sequential data, Learning nonlinear state-space models using autoencoders, Cost-sensitive sequential three-way decision modeling using a deep neural network, On a high-dimensional model representation method based on copulas, ASD+M: automatic parameter tuning in stochastic optimization and on-line learning, Multilayer bootstrap networks, The growing curvilinear component analysis (GCCA) neural network, Surrogate modeling of high-dimensional problems via data-driven polynomial chaos expansions and sparse partial least square, A deep belief network with PLSR for nonlinear system modeling, On the importance of hidden bias and hidden entropy in representational efficiency of the Gaussian-bipolar restricted Boltzmann machines, An adaptive deep Q-learning strategy for handwritten digit recognition, A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems, Understanding autoencoders with information theoretic concepts, Online sequential echo state network with sparse RLS algorithm for time series prediction, Dynamical analysis of contrastive divergence learning: restricted Boltzmann machines with Gaussian visible units, Quantum SUSAN edge detection based on double chains quantum genetic algorithm, A physically constrained variational autoencoder for geochemical pattern recognition, An unsupervised parameter learning model for RVFL neural network, Geometric learning for computational mechanics. II: Graph embedding for interpretable multiscale plasticity, Data-driven spatiotemporal modeling for structural dynamics on irregular domains by stochastic dependency neural estimation, Assessment of end-to-end and sequential data-driven learning for non-intrusive modeling of fluid flows, Independent component analysis: recent advances, Seismic Bayesian evidential learning: estimation and uncertainty quantification of sub-resolution reservoir properties, Diversity loss is predicted to increase extinction risk of specialist animals by constraining their ability to expand niche, Deep learning for generic object detection: a survey, Distance-preserving manifold denoising for data-driven mechanics, Large data sets and machine learning: applications to statistical arbitrage, \(p\)-adic statistical field theory and deep belief networks, Relational intelligence recognition in online social networks -- a survey, Soft sensor modeling of key effluent parameters in wastewater treatment process based on SAE-NN, Deep Haar scattering networks, Contrastive Divergence in Gaussian Diffusions, A study on the effects of normalized TSP features for automated algorithm selection, Establishing simple relationship between eigenvector and matrix elements, Machine learning entanglement freedom, Optimization for deep learning: an overview, Deep, Narrow Sigmoid Belief Networks Are Universal Approximators, Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning, Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders, Data-space inversion using a recurrent autoencoder for time-series parameterization, Analyzing market baskets by restricted Boltzmann machines, The Architectures of Geoffrey Hinton, Deep Variational Inference, Computational modelling of memory retention from synapse to behaviour, Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses, Machine learning algorithms based on generalized Gibbs ensembles, Resolution and relevance trade-offs in deep learning, A machine-learning approach to synthesize virtual sensors for parameter-varying systems, Nonequilibrium thermodynamics of self-supervised learning, Adversarial domain adaptation network for tumor image diagnosis, Parametric non-intrusive model order reduction for flow-fields using unsupervised machine learning, A machine learning framework for accelerating the design process using CAE simulations: an application to finite element analysis in structural crashworthiness, Deep autoencoders for physics-constrained data-driven nonlinear materials modeling, Deep learning for credit scoring: do or don't?, Data-driven reduced bond graph for nonlinear multiphysics dynamic systems, Machine learning-combined topology optimization for functionary graded composite structure design, Comments on ``Data science, big data and statistics, Unnamed Item, Large-Margin Classification in Infinite Neural Networks, Comparing Classification Methods for Longitudinal fMRI Studies, A survey of randomized algorithms for training neural networks, Prototype Classification: Insights from Machine Learning, Intelligent fuzzy sliding mode control for complex robot system with disturbances, Nonredundant sparse feature extraction using autoencoders with receptive fields clustering, Deep neural mapping support vector machines, A linear relation between input and first layer in neural networks, Supervised neural computing and LMI optimisation for order model reduction-based control of the Buck switching-mode power supply, Bounding the Bias of Contrastive Divergence Learning, A DBN-based deep neural network model with multitask learning for online air quality prediction, Neural-Network Quantum State of Transverse-Field Ising Model, Information Preserving Dimensionality Reduction, Solving for high-dimensional committor functions using artificial neural networks, Deep collective matrix factorization for augmented multi-view learning, Improving latent variable descriptiveness by modelling rather than ad-hoc factors, VISUAL HAND GESTURES CLASSIFICATION USING WAVELET TRANSFORMS, Feature extraction from telematics car driving heatmaps, Diffusion nets, A novel conjoint triad auto covariance (CTAC) coding method for predicting protein-protein interaction based on amino acid sequence, A novel parallel auto-encoder framework for multi-scale data in civil structural health monitoring, Automatic prediction of meningioma grade image based on data amplification and improved convolutional neural network, SEMISUPERVISED MULTIMODAL DIMENSIONALITY REDUCTION, Provable ICA with unknown Gaussian noise, and implications for Gaussian mixtures and autoencoders, gLaSDI: parametric physics-informed greedy latent space dynamics identification, Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks, GPLaSDI: Gaussian process-based interpretable latent space dynamics identification through deep autoencoder, Novel parameter-free and parametric same degree distribution-based dimensionality reduction algorithms for trustworthy data structure preserving, Efficient approximations of the fisher matrix in neural networks using kronecker product singular value decomposition, Deep convolutional Ritz method: parametric PDE surrogates without labeled data, Some recent trends in embeddings of time series and dynamic networks, An industrial process fault diagnosis method based on independent slow feature analysis and stacked sparse autoencoder network, Orthogonally constrained matrix factorization for robust unsupervised feature selection with local preserving, Representations of graph states with neural networks, Stability and Hopf bifurcation of fractional complex-valued BAM neural networks with multiple time delays, Wassmap: Wasserstein Isometric Mapping for Image Manifold Learning, Statistical embedding: beyond principal components, Exploring two-dimensional internal waves: a new three-coupled Davey-Stewartson system and physics-informed neural networks with weight assignment methods, Dual order-reduced Gaussian process emulators (DORGP) for quantifying high-dimensional uncertain crack growth using limited and noisy data, Back-propagating errors through artificial neural networks for variable selection, Operator approximation of the wave equation based on deep learning of Green's function, Deep random walk of unitary invariance for large-scale data representation, A survey on deep learning and its applications, Learning a multi-dimensional companding function for lossy source coding, On better training the infinite restricted Boltzmann machines, Deep kernel dimensionality reduction for scalable data integration, Image inversion and uncertainty quantification for constitutive laws of pattern formation, Deep active inference, A physics-informed and hierarchically regularized data-driven model for predicting fluid flow through porous media, General hyperplane prior distributions based on geometric invariances for Bayesian multivariate linear regression, Unsupervised 3D shape segmentation and co-segmentation via deep learning, Neural network training using \(\ell_1\)-regularization and bi-fidelity data, Accelerating phase-field predictions via recurrent neural networks learning the microstructure evolution in latent space, Learning localized features in 3D CAD models for manufacturability analysis of drilled holes, A game-theoretic analysis of deep neural networks, A topological insight into restricted Boltzmann machines, Proper orthogonal decomposition and physical field reconstruction with artificial neural networks (ANN) for supercritical flow problems, Bidirectional nonnegative deep model and its optimization in learning, Recognizing recurrent neural networks (rRNN): Bayesian inference for recurrent neural net\-works, Deep extreme learning machine and its application in EEG classification, Topologically ordered feature extraction based on sparse group restricted Boltzmann machines, Convergence analysis of contrastive divergence algorithm based on gradient method with errors, Hierarchical recognition system for target recognition from sparse representations, Nonlinear multi-output regression on unknown input manifold, Two-layer contractive encodings for learning stable nonlinear features, Expected energy-based restricted Boltzmann machine for classification, Tensorized feature extraction technique for multimodality preserving manifold visualization, The flip-the-state transition operator for restricted Boltzmann machines, A brief review of neural networks based learning and control and their applications for robots, A compact local binary pattern using maximization of mutual information for face analysis, Real-time lip reading system for isolated Korean word recognition, Training restricted Boltzmann machines: an introduction, Inductive manifold learning using structured support vector machine, Complex-valued autoencoders, On the equivalence of Hopfield networks and Boltzmann machines, Marginal semi-supervised sub-manifold projections with informative constraints for dimensionality reduction and recognition, Generating feature spaces for linear algorithms with regularized sparse kernel slow feature analysis, Model of protein fragments and statistical potentials, Semi-supervised local Fisher discriminant analysis for dimensionality reduction, Reservoir computing approaches to recurrent neural network training, Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification, Using isotope composition and other node attributes to predict edges in fish trophic networks, Deep learning in the heterotic orbifold landscape, Modeling documents with Event Model, Visualizing and understanding sum-product networks, A bound for the convergence rate of parallel tempering for sampling restricted Boltzmann machines, A CNN-based shock detection method in flow visualization, Generative adversarial networks with decoder-encoder output noises, Training of deep neural networks for the generation of dynamic movement primitives, Multi-feature gait recognition with DNN based on sEMG signals, On separating points by lines, Predicting the effective mechanical property of heterogeneous materials by image based modeling and deep learning, Thermodynamics of restricted Boltzmann machines and related learning dynamics, Convergence of contrastive divergence algorithm in exponential family, Graph-induced restricted Boltzmann machines for document modeling, A cycle deep belief network model for multivariate time series classification, Finding quasi core with simulated stacked neural networks, Boolean autoencoders and hypercube clustering complexity, Challenges in data science: a complex systems perspective, A factor graph model for unsupervised feature selection, Improved neural networks based on mutual information via information geometry, A hybrid autoencoder network for unsupervised image clustering, Non-iterative and fast deep learning: multilayer extreme learning machines, Knowledge discovery by accuracy maximization, Face recognition via deep stacked denoising sparse autoencoders (DSDSA), Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network, Deep learning for model order reduction of multibody systems to minimal coordinates, Towards blending physics-based numerical simulations and seismic databases using generative adversarial network, The neural particle method - an updated Lagrangian physics informed neural network for computational fluid dynamics, A wavelet-based learning approach assisted multiscale analysis for estimating the effective thermal conductivities of particulate composites, Nonlinear dimensionality reduction with hybrid distance for trajectory representation of dynamic texture, How adaptation makes low firing rates robust, A thermodynamic perspective of immune capabilities, Enhancing multi-document summarization using concepts, Hierarchical deep-learning neural networks: finite elements and beyond, Deep network based on stacked orthogonal convex incremental ELM autoencoders, Simplified information maximization for improving generalization performance in multilayered neural networks, Efficient regularized spectral data embedding, Deep graph similarity learning: a survey, A novel semi-supervised multi-view clustering framework for screening Parkinson's disease, Editorial: Non-iterative approaches in training feed-forward neural networks and their applications, Model reduction and neural networks for parametric PDEs, Multi-aspect renewable energy forecasting, Guest editorial: Generative adversarial networks for computer vision, A theory of incremental compression, Deep learning on image denoising: an overview, Data-driven reduced order modeling of poroelasticity of heterogeneous media based on a discontinuous Galerkin approximation, A pore space reconstruction method of shale based on autoencoders and generative adversarial networks, Network embedding: taxonomies, frameworks and applications, Recurrent neural networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step, GLRM: logical pattern mining in the case of inconsistent data distribution based on multigranulation strategy, Accurate Bayesian data classification without hyperparameter cross-validation, Deep learning and k-means clustering in heterotic string vacua with line bundles, Subspace clustering using a low-rank constrained autoencoder, Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression, Deep learning of chroma representation for cover song identification in compression domain, Learning large \(Q\)-matrix by restricted Boltzmann machines, A game-theoretic perspective of deep neural networks, A capsule-unified framework of deep neural networks for graphical programming, An iterative stacked weighted auto-encoder, \(\pi\) VAE: a stochastic process prior for Bayesian deep learning with MCMC
Uses Software
