DocumentCode
2714131
Title
Frequency based computation in neural networks
Author
Eisman, Gerald S.
Author_Institution
Dept. of Comput. Sci., San Francisco State Univ., CA, USA
fYear
1991
fDate
8-14 Jul 1991
Firstpage
577
Abstract
A model of neural network computation is presented in which the frequency of firing of a neuron is the basis upon which numerical values are measured. The author first discusses the model of the individual firing units, and then presents the constructions of the modules which purport to compute the arithmetic operations. A large network was built using these modules. It can be used to find near-optimal solutions to the task assignment problem. The proposed model is shown to produce excellent results
Keywords
biocybernetics; neural nets; arithmetic operations; frequency based computation; model; near-optimal solutions; neural networks; task assignment; Arithmetic; Biology computing; Computer networks; Computer science; Fires; Frequency measurement; Intelligent networks; Modular construction; Neural networks; Neurons;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location
Seattle, WA
Print_ISBN
0-7803-0164-1
Type
conf
DOI
10.1109/IJCNN.1991.155398
Filename
155398
Link To Document