DocumentCode :
2629258
Title :
A constant-time neural network for multiple selection
Author :
Chou, Wen-Kuang ; Yun, David Y Y ; Tseng, Chien-Chao
Author_Institution :
Telecommunication Labs., Chung-Li, Taiwan
fYear :
1991
fDate :
18-21 Nov 1991
Firstpage :
1184
Abstract :
A MAXNET with constant-time response and with multiple selection of several maximum values, CTMAXNET, is presented. The constant-time response for CTMAXNET is proved. A cost analysis of VLSI implementation for CTMAXNET is presented, and it is shown that CTMAXNET has a smaller cost than MAXNET. From the example of ART1, it is shown that including MAXNET leads to misclassification while including CTMAXNET does not. Through these results, the case is made that CTMAXNET is worthy of embedding in a large number of neural network classifier models and applications
Keywords :
neural nets; CTMAXNET; MAXNET; VLSI implementation; classifier models; constant-time neural network; cost analysis; multiple selection; Broadcasting; Computer networks; Costs; Learning systems; Network topology; Neural networks; Neurons; Time factors; Very large scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
Type :
conf
DOI :
10.1109/IJCNN.1991.170557
Filename :
170557
Link To Document :
بازگشت