Corrective memory by a symmetric sparsely encoded network

DOI10.1109/18.312165MaRDI QIDQ4308777zbMATH OpenOpenAlexFDO

Authors Yoram Baram

Publication date 10 October 1994

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

Full work available at URL https://doi.org/10.1109/18.312165

zbMATH Keywords

associative memorycorrective memoryKanerva modelneural networksparse encoding

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Storage capacities of sparse associative memories
• Lower bounds on the capacities of binary and ternary networks storing sparse random vectors
• A comparative study of sparse associative memories
• Quality and efficiency of retrieval for Willshaw-like autoassociative networks. I. Correction
• Typical error pattern recovery of the Hopfield memory under error-tolerant conditions

Cited in

(5)

• Efficient retrieval from sparse associative memory
• Foundations of the neural network assembly memory model
• Lower bounds on the capacities of binary and ternary networks storing sparse random vectors
• Storage capacities of sparse associative memories
• Quality and efficiency of retrieval for Willshaw-like autoassociative networks. I. Correction

This page was built for publication: Corrective memory by a symmetric sparsely encoded network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4308777)