yxt3@po.CWRU.Edu (Yoshiyasu Takefuji) (06/12/91)
The following reprints are available from Center for Automation and Intelligent Systems Research (CAISR) at Case Western Reserve University. Send your request to Lawrence Boyd, CAISR, Case Western Reserve University, Cleveland, OH 44106. Phone 216-368-6434. Each paper may cost $2 including handling and mailing. TR 91-131: Y. Takefuji and K. C. Lee, An artificial hysteresis binary neuron: a model suppressing the oscillatory behaviors of neural dynamics, published in Biological Cybernetics, 64, 353-356, 1991. ABSTRACT A hysteresis binary McCulloch-Pitts neuron model is proposed in order to suppress the complicated oscillatory behaviors of neural dynamics. The artificial hysteresis binary neural network is used for scheduling time-multiplex crossbar switches in order to demonstrate the effects of hysteresis. Time-multiplex crossbar switching system must control traffic on demand such that packet blocking probability and packet waiting time are minimized. The system using n x n processing elements solves an n x n crossbar-control problem with O(1) time, while the best existing parallel algorithm requires O(n) time. The hysteresis binary neural network maximizes the throughput of packets through a crossbar switch. The solution quality of our system does not degrade with the problem size.