A learning algorithm to teach spatiotemporal patterns to recurrent neural networks

  title={A learning algorithm to teach spatiotemporal patterns to recurrent neural networks},
  author={Masa-aki Sato},
  journal={Biological Cybernetics},
A new supervised learning algorithm is proposed. It teaches spatiotemporal patterns to the recurrent neural network with arbitrary feedback connections. In this method the network with fixed connection weights is run for a given period of time under a given external input and initial condition. Then the weights are changed so that the total error from the time dependent teacher signal in this period is maximally decreased. This algorithm is equivalent to the back propagation method for the… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 12 references

Gain Variation in Recurrent Error Propagation Networks

Complex Systems • 1988
View 4 Excerpts
Highly Influenced

A real time learning algorithm for recurrent analog neural networks. TIRL

M Sato
View 3 Excerpts
Highly Influenced

Energy learning in neural network model which reconstructs image from noisy data

T Ikeda, T Inui, +3 authors E Yodogawa
ITEJ Tech Rep • 1988
View 1 Excerpt

A learning rule for asynchronous perceptrons with feedback in a combinatorial environment

LB Almeida
In: Butler CM (ed) Proceedings of the 1st International Conference on Neural Networks, • 1987
View 1 Excerpt

NET talk, a parallel network that learns to read aloud

CR Rosenberg, T Sejnowski
Tech Rep, Johns Hopkis University, • 1986
View 1 Excerpt

Neurons with graded response have collective computational properties like those of two-state neurons.

Proceedings of the National Academy of Sciences of the United States of America • 1984
View 1 Excerpt

Similar Papers

Loading similar papers…