An artificial hysteresis binary neuron

a model suppressing the oscillatory behaviors of neural dynamics

Research output: Contribution to journalArticle

66 Citations (Scopus)

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 systems must control traffic on demand such that packet blocking probability and packet waiting time are minimized. The system using n×n processing elements solves an n×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.

Original languageEnglish
Pages (from-to)353-356
Number of pages4
JournalBiological Cybernetics
Volume64
Issue number5
DOIs
Publication statusPublished - 1991 Mar
Externally publishedYes

Fingerprint

Neurons
Hysteresis
Switches
Neural networks
Blocking probability
Switching systems
Traffic control
Parallel algorithms
Scheduling
Throughput
Processing

ASJC Scopus subject areas

  • Biophysics

Cite this

An artificial hysteresis binary neuron : a model suppressing the oscillatory behaviors of neural dynamics. / Takefuji, Yoshiyasu; Lee, K. C.

In: Biological Cybernetics, Vol. 64, No. 5, 03.1991, p. 353-356.

Research output: Contribution to journalArticle

@article{35dab4ba9c8247fd9137f4f65af88af1,
title = "An artificial hysteresis binary neuron: a model suppressing the oscillatory behaviors of neural dynamics",
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 systems must control traffic on demand such that packet blocking probability and packet waiting time are minimized. The system using n×n processing elements solves an n×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.",
author = "Yoshiyasu Takefuji and Lee, {K. C.}",
year = "1991",
month = "3",
doi = "10.1007/BF00224701",
language = "English",
volume = "64",
pages = "353--356",
journal = "Biological Cybernetics",
issn = "0340-1200",
publisher = "Springer Verlag",
number = "5",

}

TY - JOUR

T1 - An artificial hysteresis binary neuron

T2 - a model suppressing the oscillatory behaviors of neural dynamics

AU - Takefuji, Yoshiyasu

AU - Lee, K. C.

PY - 1991/3

Y1 - 1991/3

N2 - 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 systems must control traffic on demand such that packet blocking probability and packet waiting time are minimized. The system using n×n processing elements solves an n×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.

AB - 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 systems must control traffic on demand such that packet blocking probability and packet waiting time are minimized. The system using n×n processing elements solves an n×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.

UR - http://www.scopus.com/inward/record.url?scp=0001663243&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0001663243&partnerID=8YFLogxK

U2 - 10.1007/BF00224701

DO - 10.1007/BF00224701

M3 - Article

VL - 64

SP - 353

EP - 356

JO - Biological Cybernetics

JF - Biological Cybernetics

SN - 0340-1200

IS - 5

ER -