Title :
A product-of-norms model for recurrent neural networks
Author :
Hou, Jiansheng ; Salam, Fathi M A
Author_Institution :
Dept. of Electr. Eng., Michigan State Univ., East Lansing, MI, USA
Abstract :
The authors present a model for recurrent artificial neural networks which can store any number of any prespecified patterns as energy local minima. Therefore, all the prespecified patterns can be stored and retrieved. The authors summarize the model´s stability properties. They then give two examples, showing how this model can be used in image recognition and association
Keywords :
image recognition; recurrent neural nets; association; energy local minima; image recognition; product-of-norms model; recurrent neural networks; Adaptive control; Artificial neural networks; Circuits; Computer networks; Control systems; Image recognition; Laboratories; Neurons; Recurrent neural networks; Stability;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287164
