Title :
Some practical issues concerning the gamma neural net
Author :
De Vries, Dert ; Principe, Jose C.
Author_Institution :
Dept. of Electr. Eng., Florida Univ., Gainesville, FL, USA
Abstract :
Summary form only given, as follows. A novel neural model for processing of temporal patterns has been presented. This model, the gamma neural net, generalizes dynamic additive models with delay and/or local feedback into a unifying framework. Implementation issues regarding the gamma net were explored, and a real-time backpropagation procedure was derived. Results from a signal prediction experiment were obtained
Keywords :
computerised pattern recognition; computerised signal processing; delays; feedback; neural nets; delay; dynamic additive models; gamma neural net; local feedback; real-time backpropagation; signal prediction; temporal pattern processing; Added delay; Backpropagation; Computational modeling; Computer networks; Computer science; Distributed processing; Educational institutions; Neural networks; Neurofeedback; Prototypes;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155660
