Learning Synaptic Clusters for Nonlinear Dendritic Processing

Nonlinear dendritic processing appears to be a feature of biological neurons and would also be of use in many applications of artificial neural networks. This paper presents a model of an initially standard linear node which uses unsupervised learning to find clusters of inputs within which inactivity at one synapse can occlude the activity at the other synapses.

• Type: Journal
• Year: 2000
• Where: NPL
• Authors: Michael W. Spratling, Gillian Hayes
• Keywords: Artificial Neural Networks, Nonlinear Dendritic Processing, NPL 2000, Standard Linear Node