DocumentCode
3402668
Title
The Hopfield and the BP Nouro-humoral Network
Author
Shuhai, Fan ; Weihong, Ni ; Wen, Shen ; Wentong, Wang ; Tian-Yuan, Xiao
Author_Institution
Nanjing Univ. of Technol., Nanjing
fYear
2007
fDate
5-8 Aug. 2007
Firstpage
669
Lastpage
673
Abstract
In this article, two kinds of structures of the neural network, the Hopfield Nouro-humoral network and the BP Nouro-humoral network were brought forward. The humoral regulation was considered and successfully integrated into the neural network. First, the fundamental structure of nerve cells, which was affected by both the humor regulation and the neural regulation, was proposed. In the open loop mode, a discrete synchronous Hopfield Nouro-humoral network was analyzed and its stability was also validated. Then, for the BP Nouro-humoral network, a useful learning formula of the threshold affected by humor system in neural network was deduced. Considering the back action of the BP Nouro-humoral network to the humor system, a close loop mode system, which can be used to eliminate the error of the neural network, was proposed. Finally, in an "anesthetic mode", the conditions of the loop mode were deduced and the stability of it was also validated.
Keywords
Hopfield neural nets; backpropagation; biocontrol; cellular biophysics; closed loop systems; discrete systems; learning systems; neurophysiology; open loop systems; stability; BP Nouro-humoral network; close loop mode system; discrete synchronous Hopfield Nouro-humoral network; humoral regulation; learning formula; nerve cells; neural network; neural regulation; open loop mode; stability; Anesthetic drugs; Artificial neural networks; Automation; Biochemistry; Biological neural networks; Blood; Humans; Nervous system; Neurons; Organisms; humoral regulation; neural network; simulation;
fLanguage
English
Publisher
ieee
Conference_Titel
Mechatronics and Automation, 2007. ICMA 2007. International Conference on
Conference_Location
Harbin
Print_ISBN
978-1-4244-0828-3
Electronic_ISBN
978-1-4244-0828-3
Type
conf
DOI
10.1109/ICMA.2007.4303623
Filename
4303623
Link To Document