Related Experiment Videos

Convergence of stochastic learning in perceptrons with binary synapses.

Walter Senn1, Stefano Fusi

  • 1Department of Physiology, University of Bern, CH-3012 Bern, Switzerland. wsenn@cns.unibe.ch

Summary

This study shows that slow stochastic learning with binary synapses can enable high-probability memory storage and pattern classification. This approach overcomes limitations of discrete synaptic states in neural networks, even for complex patterns.

Related Concept Videos