Neurocontrol in Sequence Recognition

Download: gzipped pdf.

“Neurocontrol in Sequence Recognition” by W. Byrne and S. Shamma. In Progress in Neural Networks: Neural Networks for Control, (O. Omidvar and D. Elliott, eds.), 1997, pp. 31-56 (26 pages).


An artificial neural network intended for sequence modeling and recognition is described. The network is based on a lateral inhibitory network with controlled, oscillatory behavior so that it naturally models sequence generation. Dynamic programming algorithms can be used to transform the network into a sequence recognizer. Markov decision theory is used to develop novel and more “neural” recognition control strategies as alternatives to dynamic programming.

Download: gzipped pdf.

BibTeX entry:

   author = {W. Byrne and S. Shamma},
   editor = {O. Omidvar and D. Elliott},
   title = {Neurocontrol in Sequence Recognition},
   booktitle = {Progress in Neural Networks: Neural Networks for Control},
   pages = {31--56 (26 pages)},
   publisher = {Academic Press},
   year = {1997}

Back to Bill Byrne publications.