For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Fast Neural Network Simulator for State Transition Analysis
Atsushi KAMO Hiroshi NINOMIYA Teru YONEYAMA Hideki ASAI
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1999/09/25
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Nonlinear Theory and Its Applications)
stepwise constant method, multivalued neural network, ASSIST, state transition analysis,
Full Text: PDF>>
This paper describes an efficient simulator for state transition analysis of multivalued continuous-time neural networks, where the multivalued transfer function of neuron is regarded as a stepwise constant one. Use of stepwise constant method enables to analyse the state transition of the network without solving explicitly the differential equations. This method also enables to select the optimal timestep in numerical integration. The proposed method is implemented on the simulator and applied to the general neural network analysis. Furthermore, this is compared with the conventional simulators. Finally, it is shown that our simulator is drastically faster and more practical than the conventional simulators.