Capacity of two-layer feedforward neural networks with binary weights

DOI10.1109/18.651033MaRDI QIDQ4392451zbMATH OpenOpenAlexFDO

Authors Chuanyi Ji, Demetri Psaltis

Publication date 22 February 1999

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://infoscience.epfl.ch/record/158446/files/IEEE_44_256_Jan1998.pdf, http://infoscience.epfl.ch/record/158446

zbMATH Keywords

binary interconnectionsbinary weightsfeedforward neural networksinformation capacitymultilayer networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Measures of information, entropy (94A17)

Recommendations

• On the capacity of neural networks with binary weights
• Bounds on the learning capacity of some multi-layer networks
• ON THE CAPACITY OF MULTILAYER NEURAL NETWORKS TRAINED WITH BACKPROPAGATION
• On neuronal capacity

Cited in

(8)

• Lower bound for connectivity in local-learning neural networks
• Bounds on the learning capacity of some multi-layer networks
• The capacity of feedforward neural networks
• Decomposition method for calculating the weights of a binary neural network
• On the capacity of neural networks with binary weights
• Feedforward neural structures in binary hypothesis testing
• ON THE CAPACITY OF MULTILAYER NEURAL NETWORKS TRAINED WITH BACKPROPAGATION
• On neuronal capacity

This page was built for publication: Capacity of two-layer feedforward neural networks with binary weights

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4392451)