Title :
Relating Bayesian learning to training in recurrent networks
Author_Institution :
Dept. of Comput., London Univ., UK
Abstract :
It is demonstrated that a recurrent neural network relying on an error correcting learning algorithm and a localist coding scheme is able to converge to a solution that would be expected from Bayesian learning. This is possible even without implementing Bayes theorem and without assigning prior probabilities to the model.
Keywords :
Bayes methods; error correction; learning (artificial intelligence); recurrent neural nets; Bayesian learning; error correcting learning algorithm; localist coding; neural network; recurrent networks; Bayesian methods; Educational institutions; Error correction; Intelligent networks; Neural networks; Probability; Psychology; Recurrent neural networks; Statistics; Training data;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223811
