Beyond Hebb: Exclusive-OR and Biological Learning
- 27 March 2000
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 84 (13) , 3013-3016
- https://doi.org/10.1103/physrevlett.84.3013
Abstract
A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-OR (XOR) problem without the aid of error backpropagation, as well as to increase robustness of learning in the presence of noise.All Related Versions
This publication has 20 references indexed in Scilit:
- Learning from mistakesNeuroscience, 1999
- D1/D5 Dopamine Receptors Inhibit Depotentiation at CA1 Synapses via cAMP-Dependent MechanismJournal of Neuroscience, 1998
- Glucocorticoid Receptor Activation Lowers the Threshold for NMDA-Receptor-Dependent Homosynaptic Long-Term Depression in the Hippocampus Through Activation of Voltage-Dependent Calcium ChannelsJournal of Neurophysiology, 1997
- Metaplasticity: A new vista across the field of synaptic plasticityProgress in Neurobiology, 1997
- Reinforcement Learning: A SurveyJournal of Artificial Intelligence Research, 1996
- Metaplasticity: the plasticity of synaptic plasticityTrends in Neurosciences, 1996
- How Nature WorksPublished by Springer Nature ,1996
- Reinforcement LearningPublished by Springer Nature ,1992
- Learning representations by back-propagating errorsNature, 1986
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943