Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units
From MaRDI portal
Publication:5383782
DOI10.1162/NECO_a_00601zbMath1419.62014arXiv1303.7461OpenAlexW2039661710WikidataQ51096063 ScholiaQ51096063MaRDI QIDQ5383782
Publication date: 20 June 2019
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1303.7461
Learning and adaptive systems in artificial intelligence (68T05) Combinatorial probability (60C05) Statistical aspects of information-theoretic topics (62B10)
Related Items (4)
Estimation of a regression function on a manifold by fully connected deep neural networks ⋮ Nonparametric regression using deep neural networks with ReLU activation function ⋮ Approximating smooth functions by deep neural networks with sigmoid activation function ⋮ Factorized mutual information maximization
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Multilayer feedforward networks are universal approximators
- Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines
- 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
- Deep Belief Networks Are Compact Universal Approximators
- Mixture decompositions of exponential families using a decomposition of their sample spaces
- Optimally approximating exponential families
- A Fast Learning Algorithm for Deep Belief Nets
- Discrete Restricted Boltzmann Machines
This page was built for publication: Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units
