Archive for July 27th, 2006

A Synapse Plasticity Model for Conceptual Drift Problems

Traditional supervised learning techniques do not address online learning problems such as concept drift, due to the fact that learning is offine when using these methods. Associative neural networks using Hebbian learning rules show robust performance in classification tasks involving concept drift. Biologically plausible neural networks represent a set of computational models designed to be more strongly related to biological neuron models. In this paper, we apply a biologically inspired plasticity model of synapse dynamics to a concept drift classification problem. The motivation for this method is to provide more biologically plausible networks in cognitive tasks.

Read the paper:

A Synapse Plasticity Model for Conceptual Drift Problems

by Chip Mappus, Ashwin Ram

28th Annual Conference of the Cognitive Science Society (CogSci-06), Vancouver, BC, July 2006