Title :
Moderatism: new concept for self-organization of neural networks
Author :
Okabe, Yoichi ; Kouhara, Takashi ; Hayashi, Hideki ; Narusawa, Atsushi ; Kitagawa, Manabu ; Miyao, Mitsuo
Author_Institution :
Res. Center for Adv. Sci. & Technol., Tokyo Univ., Japan
Abstract :
A self-organization mechanism, “moderatism” is proposed, by which the input-to-output relationship of neural networks is automatically formed so as to adapt to the environment, even if there are feedback loops inside and/or outside. By applying this organization mechanism, it is shown that the networks acquire the reflex to avoid the dangerous stimulus. Also the networks start self-oscillation by themselves to get some amount of stimulus when there is no external signal
Keywords :
feedback; neurophysiology; oscillations; self-organising feature maps; I/O relationship; feedback loops; input-to-output relationship; moderatism; neural networks; self-organization; self-oscillation; Biological neural networks; Concurrent computing; Delay; Error correction; Feedback loop; Large scale integration; Neck; Neural networks; Neurofeedback; Neurons;
Conference_Titel :
Knowledge-Based Intelligent Electronic Systems, 1998. Proceedings KES '98. 1998 Second International Conference on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-4316-6
DOI :
10.1109/KES.1998.725979
