Connectionist learning procedures
Artificial Intelligence
Parallel distributed processing: explorations in the microstructure, vol. 2: psychological and biological models
Training with noise is equivalent to Tikhonov regularization
Neural Computation
Neural Computation
Fields of Experts: A Framework for Learning Image Priors
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A fast learning algorithm for deep belief nets
Neural Computation
An empirical evaluation of deep architectures on problems with many factors of variation
Proceedings of the 24th international conference on Machine learning
Non-linear latent factor models for revealing structure in high-dimensional data
Non-linear latent factor models for revealing structure in high-dimensional data
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
IEEE Transactions on Image Processing
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Learning Deep Architectures for AI
Foundations and Trends® in Machine Learning
Why Does Unsupervised Pre-training Help Deep Learning?
The Journal of Machine Learning Research
Deep belief networks are compact universal approximators
Neural Computation
Research frontier: deep machine learning--a new frontier in artificial intelligence research
IEEE Computational Intelligence Magazine
The Journal of Machine Learning Research
Discriminative deep belief networks for visual data classification
Pattern Recognition
A connection between score matching and denoising autoencoders
Neural Computation
Higher order contractive auto-encoder
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part II
On the expressive power of deep architectures
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
Trends and advances in speech recognition
IBM Journal of Research and Development
Random search for hyper-parameter optimization
The Journal of Machine Learning Research
An efficient learning procedure for deep boltzmann machines
Neural Computation
Learning where to attend with deep architectures for image tracking
Neural Computation
Neural Networks
Features' weight learning towards improved query classification
AIS'12 Proceedings of the Third international conference on Autonomous and Intelligent Systems
From sBoW to dCoT marginalized encoders for text representation
Proceedings of the 21st ACM international conference on Information and knowledge management
Learning compact class codes for fast inference in large multi class classification
ECML PKDD'12 Proceedings of the 2012 European conference on Machine Learning and Knowledge Discovery in Databases - Volume Part I
Energy-based temporal neural networks for imputing missing values
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part II
Online multimodal deep similarity learning with application to image retrieval
Proceedings of the 21st ACM international conference on Multimedia
Nonparametric guidance of autoencoder representations using label information
The Journal of Machine Learning Research
Deep learning of representations: looking forward
SLSP'13 Proceedings of the First international conference on Statistical Language and Speech Processing
Demystifying sparse rectified auto-encoders
Proceedings of the Fourth Symposium on Information and Communication Technology
Training energy-based models for time-series imputation
The Journal of Machine Learning Research
The dropout learning algorithm
Artificial Intelligence
Hi-index | 0.00 |
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We introduce and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. This approach can be used to train autoencoders, and these denoising autoencoders can be stacked to initialize deep architectures. The algorithm can be motivated from a manifold learning and information theoretic perspective or from a generative model perspective. Comparative experiments clearly show the surprising advantage of corrupting the input of autoencoders on a pattern classification benchmark suite.