Combining Hebbian and reinforcement learning in a minibrain model

DOI10.1016/J.NEUNET.2003.07.007MaRDI QIDQ1887119zbMATH OpenOpenAlexDBLPWikidataFDO

Authors R. J. C. Bosman, W. A. van Leeuwen, B. Wemmenhove

Publication date 23 November 2004

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/0301627

zbMATH Keywords

Biological neural networkHebbian learningMinibrain model

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: A toy model of a neural network in which both Hebbian learning and reinforcement learning occur is studied. The problem of `path interference', which makes that the neural net quickly forgets previously learned input-output relations is tackled by adding a Hebbian term (proportional to the learning rate $eta$) to the reinforcement term (proportional to $ho$) in the learning rule. It is shown that the number of learning steps is reduced considerably if $1/4<eta/ho<1/2$, i.e., if the Hebbian term is neither too small nor too large compared to the reinforcement term.

Recommendations

• Reward-modulated Hebbian learning of decision making
• Reinforcement learning in spiking neural networks with stochastic and deterministic synapses
• scientific article; zbMATH DE number 1928688
• scientific article; zbMATH DE number 2033135
• A maximum likelihood Hebbian learning-based method to an agent-based architecture

Cites work

• Derivation of Hebb's rule
• scientific article; zbMATH DE number 48808 (Why is no real title available?)
• scientific article; zbMATH DE number 3231758 (Why is no real title available?)

Cited in

(3)

• Short-term plasticity as cause-effect hypothesis testing in distal reward learning
• scientific article; zbMATH DE number 1928688 (Why is no real title available?)
• A two-step algorithm for learning from unspecific reinforcement

This page was built for publication: Combining Hebbian and reinforcement learning in a minibrain model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1887119)