Learning sensory-motor cortical mappings without training

Spratling, Michael and Hayes, Gillian (1998) Learning sensory-motor cortical mappings without training. [Conference Paper]

Full text available as:

[img] Postscript


This paper shows how the relationship between two arrays of artificial neurons, representing different cortical regions, can be learned. The algorithm enables each neural network to self-organise into a topological map of the domain it represents at the same time as the relationship between these maps is found. Unlike previous methods learning is achieved without a separate training phase; the algorithm which learns the mapping is also that which performs the mapping.

Item Type:Conference Paper
Keywords:sensorimotor control, neural networks
Subjects:Computer Science > Neural Nets
Computer Science > Robotics
Neuroscience > Neural Modelling
ID Code:1106
Deposited By: Spratling, Dr Michael
Deposited On:15 Nov 2000
Last Modified:11 Mar 2011 08:54


Repository Staff Only: item control page