The capacity of feedforward neural networks

DOI10.1016/j.neunet.2019.04.009zbMath1434.68498arXiv1901.00434OpenAlexW2962715412WikidataQ92274783 ScholiaQ92274783MaRDI QIDQ2183684

Pierre Baldi, R. V. Vershinin

Publication date: 27 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1901.00434

zbMATH Keywords

complexityneural networkscapacitydeep learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items

Memory Capacity of Neural Networks with Threshold and Rectified Linear Unit Activations, A theory of capacity and sparse neural encoding, The quarks of attention: structure and capacity of neural attention building blocks, On neuronal capacity, Unnamed Item, Polynomial Threshold Functions, Hyperplane Arrangements, and Random Tensors

Cites Work

• Boolean autoencoders and hypercube clustering complexity
• Multilayer feedforward networks are universal approximators
• Discrete Mathematics of Neural Networks
• High-Dimensional Probability
• On the Probability That a Random ± 1-Matrix Is Singular
• On Complete Sets of Logic Primitives
• Enumeration of Seven-Argument Threshold Functions
• Partitions ofN-Space by Hyperplanes
• A logical calculus of the ideas immanent in nervous activity
• Approximation by superpositions of a sigmoidal function
• Unnamed Item
• Unnamed Item
• Unnamed Item