DocumentCode :
3226857
Title :
Information geometry of differentially fed artificial neural networks
Author :
Manjunath, R. ; Gurumurth, K.S.
Author_Institution :
Dept.of EC & CSE UVCE, Bangalore, India
Volume :
3
fYear :
2002
fDate :
28-31 Oct. 2002
Firstpage :
1521
Abstract :
A new class of neural networks with differential feedback are presented. The different orders of differential feedback form a manifold of hyperplanes, one among them called eigen-plane corresponding to ∞ order feedback. In this paper information geometry is used to explore the interesting properties of this plane.
Keywords :
entropy; feedback; neural nets; probability; differential feedback; eigen plane; entropy; hyperplanes; information geometry; neural networks; probability distributions; Artificial neural networks; Distributed computing; Feeds; Information geometry; Joining processes; Multilayer perceptrons; Neural networks; Neurofeedback; Output feedback; Probability distribution;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
TENCON '02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering
Print_ISBN :
0-7803-7490-8
Type :
conf
DOI :
10.1109/TENCON.2002.1182618
Filename :
1182618
Link To Document :
بازگشت