Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation
Explore this paper's citation graph
Summary
A way of modeling high-dimensional data vectors by using an unsupervised, nonlinear, multilayer neural network in which the activity of each neuron-like unit makes an additive contribution to a global energy score that indicates how surprised the network is by the data vector.
- Type
- article
- Published
- 2006-07-08
- Cited by
- 155
- References
- 13
- OpenAlex
- https://openalex.org/W2108581046
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:6433677
Keywords
Artificial neural network, Energy (signal processing), Nonlinear system, Backpropagation, Computer science
References
- The "independent components" of natural scenes are edge filters.
- What is Cognitive Science
- Learning representations by back-propagating errors
- Modelling the Statistics of Natural Images with Topographic Product of Student-t Models
- Discovering Multiple Constraints that are Frequently Approximately Satisfied
- Independent component filters of natural images compared with simple cells in primary visual cortex
- Training Products of Experts by Minimizing Contrastive Divergence
- A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images.
- Topographic Product Models Applied to Natural Scene Statistics
- Emergence of simple-cell receptive field properties by learning a sparse code for natural images
- Backpropagation Through Time: What It Does and How to Do It
- Bayesian learning for neural networks
Cited by
- Deep Architectures for Baby AI
- Approximation and Relaxation Approaches for Parallel and Distributed Machine Learning
- Learning generative models of mid-level structure in natural images
- On the Expressive Efficiency of Sum Product Networks
- Distributed representations for compositional semantics
- Learning techniques for multi-modal facial analysis
- Modeling Image Structure with Factorized Phase-Coupled Boltzmann Machines
- Generative Modeling of Convolutional Neural Networks
- Automatic Image Annotation Using Convex Deep Learning Models
- Modeling pixel means and covariances using factorized third-order boltzmann machines
- Accurate estimation of large-scale IP traffic matrix
- Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition
- Learning Non-linear Reconstruction Models for Image Set Classification
- Learning Deep Architectures for AI
- Deep Reconstruction Models for Image Set Classification
- Neural Conditional Energy Models for Multi-label Classification
- Learning Generative Texture Models with extended Fields-of-Experts
- Computational models of location-invariant orthographic processing
- The Role of Syntax in Vector Space Models of Compositional Semantics
- On the Representational Efficiency of Restricted Boltzmann Machines
Related papers
- Standard and Advanced Backpropagation Models for Image Processing Application in Traffic Engineering
- Genetic Algorithm and Neural Network for optical Character Recognition
- Adaptability of the backpropagation procedure
- Backpropagation and F-adjoint
- PERAMALAN MENGGUNAKAN METODE BACKPROPAGATION NEURAL NETWORK
- SALES PREDICTION OF ANUGERAH JAYA PANCING 99 SHOP WITH BACKPROPAGATION NEURAL NETWORKS
- Study of Neural Network Methods in Predicting Protein Secondary Structures
- Severity measurements using neural networks