Differentially fed neural networks as ideal estimators in Bayesian space

Authors:
R. Manjunath;K. S. Gurumurthy
Affiliations:
Bangalore University, Dept of EC & CSE, UVCE, Bangalore, India;Bangalore University, Dept of EC & CSE, UVCE, Bangalore, India
Venue:
ICECS'03 Proceedings of the 2nd WSEAS International Conference on Electronics, Control and Signal Processing
Year:
2003

Citing 2
Cited 0

Simulated annealing and Boltzmann machines: a stochastic approach to combinatorial optimization and neural computing

Simulated annealing and Boltzmann machines: a stochastic approach to combinatorial optimization and neural computing
Information geometry of the EM and em algorithms for neural networks

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The interactions among a family of probability distributions can be studied under Information Geometry. With Bayesian decision theory, these interactions lead to the concept of "ideal estimates". In this paper the concept of differential feedback is added to Information geometry. Here the probability distribution is mapped on to the hyperplanes with ideal estimates on the Eigenplane.