Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 1 of 1
Full-Text Articles in Entire DC Network
Preparing More Effective Liquid State Machines Using Hebbian Learning, David Norton, Dan A. Ventura
Preparing More Effective Liquid State Machines Using Hebbian Learning, David Norton, Dan A. Ventura
Faculty Publications
In Liquid State Machines, separation is a critical attribute of the liquid—which is traditionally not trained. The effects of using Hebbian learning in the liquid to improve separation are investigated in this paper. When presented with random input, Hebbian learning does not dramatically change separation. However, Hebbian learning does improve separation when presented with real-world speech data.