Optimising synaptic learning rules in linear associative memories

DOI10.1007/BF00206223zbMath0752.92002WikidataQ52102309 ScholiaQ52102309MaRDI QIDQ1182329

Peter Dayan, D. J. Willshaw

Publication date: 28 June 1992

Published in: Biological Cybernetics (Search for Journal in Brave)

zbMATH Keywords

learning rule; associative matrix memory; covariance rule; linear associative memories; maximization of the signal-to-noise ratio; synaptic learning rules

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

92C20: Neural biology

92B20: Neural networks for/in biological studies, artificial life and related topics

Related Items

Associative Memory with Dynamic Synapses, Spike-Timing-Dependent Plasticity and Relevant Mutual Information Maximization, Memory Capacities for Synaptic and Structural Plasticity, Inhomogeneities in Heteroassociative Memories with Linear Learning Rules, Binary Willshaw learning yields high synaptic capacity for long-term familiarity memory, Effective Neuronal Learning with Ineffective Hebbian Learning Rules, Neural Associative Memory with Optimal Bayesian Learning, Memory Dynamics in Attractor Networks with Saliency Weights

Cites Work

• Unnamed Item
• Unnamed Item
• Neural networks and physical systems with emergent collective computational abilities.
• The space of interactions in neural network models
• Correlation Matrix Memories