A real time learning algorithm for recurrent analog neural networks |
| |
Authors: | Masa-aki Sato |
| |
Institution: | (1) Telematique International Research Laboratory, Column Minami Aoyama 7F, 7-1-5 Minami Aoyama, Minato-ku, 107 Tokyo, Japan;(2) M.G.C.S. Inc., 2nd Research Office, Engineering Research Laboratory, 2-3-8 Shimomeguro, Meguro-ku, 153 Tokyo, Japan |
| |
Abstract: | A new learning algorithm is described for a general class of recurrent analog neural networks which ultimately settle down to a steady state. Recently, Pineda (Pineda 1987; Almeida 1987; Ikeda et al. 1988) has introduced a learning rule for the recurrent net in which the connection weights are adjusted so that the distance between the stable outputs of the current system and the desired outputs will be maximally decreased. In this method, many cycles are needed in order to get a target system. In each cycle, the recurrent net is run until it reaches a stable state. After that, the weight change is calculated by using a linearized recurrent net which receives the current error of the system as a bias input. In the new algorithm the weights are changed so that the total error of neuron outputs over the entire trajectory is minimized. The weights are adjusted in real time when the network is running. In this method, the trajectory to the target system can be controlled, whereas Pineda's algorithm only controls the position of the fixed point. The relation to the back propagation method (Hinton et al. 1986) is also discussed. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|