Title :
The new nondeterministic model of sigmoidal neural network
Author :
Goryashko, A.P. ; Shura-Bura, A.E.
Author_Institution :
Inst. Res. Lab., Program Syst. Inst., Pereslavi-Zalessaku, Russia
Abstract :
A new way to derive an artificial neural network of sigmoidal neurons from a nondeterministic model of logic circuits is presented. It can be used to classify the behavior of biological neural nets and of methods for synthesising fuzzy integrated-circuit chips. Some results of a computer simulation of a sigmoidal network from logic elements are examined. The most promising feature of the proposed approach is its consideration of networks which can be determined by some general rules of growth. With these rules, only the region where the network connections needs to be known, i.e. exact addresses for connections are not required
Keywords :
digital simulation; fuzzy logic; integrated logic circuits; neural chips; neural nets; biological neural nets; computer simulation; fuzzy integrated-circuit chips; growth rules; logic circuits; logic elements; network connections; nondeterministic model; sigmoidal neural network; Artificial neural networks; Biological neural networks; Biological system modeling; Boolean functions; Circuits; Computer networks; Laboratories; Network synthesis; Neural networks; Neurons;
Conference_Titel :
Neuroinformatics and Neurocomputers, 1992., RNNS/IEEE Symposium on
Conference_Location :
Rostov-on-Don
Print_ISBN :
0-7803-0809-3
DOI :
10.1109/RNNS.1992.268634
