DocumentCode
2614288
Title
Parameter determination for an implementable feedback neural network
Author
Ling, Bo ; Salam, Fathi M A
Author_Institution
Dept. of Electr. Eng., Michigan State Univ., East Lansing, MI, USA
fYear
1993
fDate
3-6 May 1993
Firstpage
2576
Abstract
The authors describe a method which ensures a designed neural network to be implementable as an electronic circuit. The approach involves two steps: (1) adjust the slope of the sigmoidal function of each neuron based on a given criterion; (2) find the weight matrix by an analytical learning algorithm. It is shown that the slope of the sigmoidal function around the origin plays an important role in the implementable neural network design. Based on the approach, the resistance in the neural circuit can be made very large, which reduces the network power dissipation
Keywords
learning (artificial intelligence); network parameters; neural chips; recurrent neural nets; analytical learning algorithm; electronic circuit; implementable feedback neural network; network power dissipation; resistance; sigmoidal function; weight matrix; CMOS technology; Circuit synthesis; Circuits and systems; Electronic circuits; Laboratories; Neural networks; Neurofeedback; Neurons; Power dissipation; Very large scale integration;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location
Chicago, IL
Print_ISBN
0-7803-1281-3
Type
conf
DOI
10.1109/ISCAS.1993.394292
Filename
394292
Link To Document