Title :
A self-organizing reasoning neural network
Author :
Dong, Lijun ; Ming, Yu
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
fDate :
27 Jun-2 Jul 1994
Abstract :
In this paper, the design of the feedforward neural network is formulated as a Bayesian-Gaussian reasoning problem. The output of the network is an optimal solution of the a posteriori probability density function. The parameters of the network can be set immediately when the training data are known. The self-organizing ability of the network can also be easily designed based on the reasoning model, thus even when the training samples become increasingly large, the network is able to optimize its parameters in an optimal way. Simulation shows that the reasoning neural network is comparable to or better than the well-known BP network in nonlinear stochastic prediction problems, and the self-organizing neural network is superior to the fixed parameter network in performance
Keywords :
Bayes methods; Gaussian distribution; feedforward neural nets; inference mechanisms; learning (artificial intelligence); probability; self-organising feature maps; Bayesian-Gaussian reasoning problem; a posteriori probability density function; feedforward neural network; nonlinear stochastic prediction problems; self-organizing reasoning neural network; Bayesian methods; Design automation; Design optimization; Equations; Feedforward neural networks; Neural networks; Predictive models; Probability density function; Stochastic processes; Training data;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374384