Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion

MaRDI QIDQ2896192zbMATH OpenFDO

Authors Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol

Publication date 13 July 2012

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL http://www.jmlr.org/papers/v11/vincent10a.html

zbMATH Keywords

deep learningdenoisingautoencodersdeep belief networksunsupervised feature learning

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Extracting and inserting knowledge into stacked denoising auto-encoders
• An iterative stacked weighted auto-encoder

Cited in

(89)

• A survey on deep learning and its applications
• MIDIA: exploring denoising autoencoders for missing data imputation
• Generative adversarial networks with decoder-encoder output noises
• Deep collective matrix factorization for augmented multi-view learning
• An iterative stacked weighted auto-encoder
• Deep belief network based on noisy data and clean data
• Nonparametric guidance of autoencoder representations using label information
• Multi-granularity sequential three-way recommendation based on collaborative deep learning
• A hybrid inference system for improved curvature estimation in the level-set method using machine learning
• An introduction to machine learning: a perspective from statistical physics
• The role of mutual information in variational classifiers
• A novel parallel auto-encoder framework for multi-scale data in civil structural health monitoring
• Network behavior recognition based on stacked automatic encoder
• A hybrid autoencoder network for unsupervised image clustering
• Denoising cosine similarity: a theory-driven approach for efficient representation learning
• Face recognition via deep stacked denoising sparse autoencoders (DSDSA)
• Manifold-based synthetic oversampling with manifold conformance estimation
• WSN optimization for sampling-based signal estimation using semi-binarized variational autoencoder
• Two-stage submodular maximization under curvature
• Neural natural language processing for unstructured data in electronic health records: a review
• Attributed network embedding via subspace discovery
• Generative imaging and image processing via generative encoder
• Latent-space inversion (LSI): a deep learning framework for inverse mapping of subsurface flow data
• Entropy-based guidance of deep neural networks for accelerated convergence and improved performance
• Graph-induced restricted Boltzmann machines for document modeling
• High-Dimensional Precision Medicine From Patient-Derived Xenografts
• TPNE: topology preserving network embedding
• Bayesian regularized artificial neural networks for the estimation of the probability of default
• Towards blending physics-based numerical simulations and seismic databases using generative adversarial network
• On Kernel Method–Based Connectionist Models and Supervised Deep Learning Without Backpropagation
• Enhancing the momentum strategy through deep regression
• The use of autoencoders for training neural networks with mixed categorical and numerical features
• Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
• Spatial-frequency domain nonlocal total variation for image denoising
• Towards understanding sparse filtering: a theoretical perspective
• On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
• STDP-compatible approximation of backpropagation in an energy-based model
• What regularized auto-encoders learn from the data-generating distribution
• scientific article; zbMATH DE number 7306871 (Why is no real title available?)
• Two-layer contractive encodings for learning stable nonlinear features
• Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems
• Genome-wide association study-based deep learning for survival prediction
• Why does unsupervised pre-training help deep learning?
• Computer model calibration with time series data using deep learning and quantile regression
• Dynamical variational autoencoders: a comprehensive review
• Deep learning techniques for medical image segmentation and object recognition
• Interpreting rate-distortion of variational autoencoder and using model uncertainty for anomaly detection
• Centered kernel alignment enhancing neural network pretraining for MRI-based dementia diagnosis
• Comments on ``Data science, big data and statistics
• A Fast Learning Algorithm for Deep Belief Nets
• Hierarchical recognition system for target recognition from sparse representations
• On Whole-Graph Embedding Techniques
• Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints
• Two-stage BP maximization under \(p\)-matroid constraint
• Unsupervised knowledge-transfer for learned image reconstruction
• Learning deep discriminative representations with pseudo supervision for image clustering
• Household financial health: a machine learning approach for data-driven diagnosis and prescription
• Extracting and inserting knowledge into stacked denoising auto-encoders
• Transport analysis of infinitely deep neural network
• Convolutional neural network learning for generic data classification
• A surrogate reduced order model of the unsteady advection dominant problems based on combination of deep autoencoders-LSTM and POD
• Dynamic image clustering from projected coordinates of deep similarity learning
• Manifold learning for coherent design interpolation based on geometrical and topological descriptors
• Subspace clustering using a low-rank constrained autoencoder
• Low rank tensor manifold learning
• Representation learning for clustering via building consensus
• GSNs: generative stochastic networks
• Deep networks for system identification: a survey
• Robust manifold broad learning system for large-scale noisy chaotic time series prediction: a perturbation perspective
• Transport model for feature extraction
• Deep Learning Approach Based on Fault Correction Time for Reliability Assessment of Cloud and Edge Open Source Software
• A review on deep learning in medical image reconstruction
• Deep learning for natural language processing: a survey
• A fast SVD-hidden-nodes based extreme learning machine for large-scale data analytics
• Large Margin Low Rank Tensor Analysis
• Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
• A probabilistic approximate logic for neuro-symbolic learning and reasoning
• Design and Implementation of a Novel Hybrid Rental Apartment Recommender System
• A Connection Between Score Matching and Denoising Autoencoders
• Structure-preserving deep learning
• Two-stage BP maximization under \(p\)-matroid constraint
• Visualizing and understanding sum-product networks
• A survey of randomized algorithms for training neural networks
• Error-correcting neural networks for semi-Lagrangian advection in the level-set method
• Deep learning from a statistical perspective
• Deep fiducial inference
• Evolutionary multi-objective design of autoencoders for compact representation of histopathology whole slide images
• KNN loss and deep KNN
• Supervised representation learning for multi-label classification

This page was built for publication: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2896192)