Title :
Bifurcations in the learning of recurrent neural networks
Author_Institution :
Dept. of Biol., California Univ., San Diego, CA, USA
Abstract :
Gradient descent algorithms in recurrent neural networks can have problems when the network dynamics experience bifurcations in the course of learning. The possible hazards caused by the bifurcations of the network dynamics and the learning equations are investigated. The roles of teacher forcing, preprogramming of network structures, and the approximate learning algorithms are discussed
Keywords :
bifurcation; learning (artificial intelligence); recurrent neural nets; bifurcations; learning; learning algorithms; learning equations; network dynamics; network structures; preprogramming; recurrent neural networks; teacher forcing; Bifurcation; Biological neural networks; Biological system modeling; Equations; Feedforward systems; Hazards; Intelligent networks; Recurrent neural networks; Speech recognition; Supervised learning;
Conference_Titel :
Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-0593-0
DOI :
10.1109/ISCAS.1992.230622
