Neural processor which can calculate a norm or a distance

作者: Yannick Deville

DOI:

关键词:

摘要: A neural processor, comprising calculation apparatus (30, NQ, RQ) which extracts a root Q of quantity X, said constituting either norm data or distance between data. The calculates (30) by iteration series contributions ΔQ i are used (NQ, to update partial QP becomes the at end calculation. can be performed on an arbitrary arithmetic base determines number neurons utilized and also accuracy It is possible execute remainder (NR, RR). Several programming modes presented.

参考文章(12)
Tony Hurson, Salim A. Shah, Stephen D. McIntyre, Ken Tseng, Thomas W. Lynch, High speed divider with square root capability ,(1990)
Hideki Yoshizawa, Hiroki Iciki, Hiroyuki Tsuzuki, Toshiharu Matsuda, Hideki Kato, Hiromu Iwamoto, Katsuya Ishikawa, Yoshihide Sugiura, Chikara Tsuchiya, Takashi Kawasaki, Hideichi Endo, Kazuo Asakawa, Neurocomputer with analog signal bus ,(1989)
William E. Weidemann, Neural network image processing system ,(1990)
Marc Duranton, Jean Gobert, Jacques-Ariel Sirat, Neural network system and circuit for use therein ,(1988)
Renals, Rohwer, Phoneme classification experiments using radial basis functions international joint conference on neural network. pp. 461- 467 ,(1989) , 10.1109/IJCNN.1989.118620
M.T. Musavi, W. Ahmed, K.H. Chan, K.B. Faris, D.M. Hummels, Original Contribution: On the training of radial basis function classifiers Neural Networks. ,vol. 5, pp. 595- 603 ,(1992) , 10.1016/S0893-6080(05)80038-3
Dennis J. Volper, Steven E. Hampson, Quadratic function nodes: use, structure and training Neural Networks. ,vol. 3, pp. 93- 107 ,(1990) , 10.1016/0893-6080(90)90048-P
R. Lippmann, An introduction to computing with neural nets IEEE ASSP Magazine. ,vol. 4, pp. 4- 22 ,(1987) , 10.1109/MASSP.1987.1165576