Deep Belief Networks Are Compact Universal Approximators
From MaRDI portal
Publication:3583502
DOI10.1162/neco.2010.08-09-1081zbMath1195.68079OpenAlexW2111838090MaRDI QIDQ3583502
Yoshua Bengio, Nicolas Le Roux
Publication date: 17 August 2010
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/neco.2010.08-09-1081
Related Items
Features Reweighting and Selection in ligand-based Virtual Screening for Molecular Similarity Searching Based on Deep Belief Networks, Exploiting layerwise convexity of rectifier networks with sign constrained weights, Approximation Analysis of Convolutional Neural Networks, Incompressible rubber thermoelasticity: a neural network approach, Complex-valued autoencoders, Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units, Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines, Deep learned finite elements, A survey of randomized algorithms for training neural networks, Optimal adaptive control of partially uncertain linear continuous-time systems with state delay
Cites Work
- On the power of small-depth threshold circuits
- Connectionist learning of belief networks
- Training Products of Experts by Minimizing Contrastive Divergence
- Learning Deep Architectures for AI
- Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
- Deep, Narrow Sigmoid Belief Networks Are Universal Approximators
- A Fast Learning Algorithm for Deep Belief Nets
