Preparing More Effective Liquid State Machines Using Hebbian Learning

—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.

• Type: Conference
• Year: 2006
• Where: IJCNN
• Authors: David Norton, Dan Ventura
• Keywords: Critical Attribute, Hebbian Learning, IJCNN 2006, Liquid State Machines