Paper

Learning Representations by Recirculation

Summary form only given, as follows. A new learning procedure for networks that contain several groups of nonlinear units arranged in a closed loop is described. The procedure modifies the weights on the connections between groups so that the training patterns over the input group return unaltered after passing around the loop. The learning rule amounts to changing each weight by an amount proportional to the product of the presynaptic activity and the rate of change of the postsynaptic activity. It is much simpler to implement in hardware than methods like back-propagation. Simulations show that it usually converges rapidly, and analysis shows that in certain restricted cases it performs gradient descent in a measure of how much the training patterns are altered by passing around the loop.

http://papers.nips.cc/paper/78-learning-representations-by-recirculation.pdfPublished 1987-01-01Paper link

Authors: Geoffrey E. Hinton · James L. McClelland

Topics

Relevant entities

People

Related coverage

Linked coverage will appear here.

Related events

Linked events will appear here.

Related discussions

Related discussion nodes will appear here.