Host: The Japanese Society for Artificial intelligence
Name : 96th SIG-FPAI
Number : 96
Location : [in Japanese]
Date : January 13, 2014 - January 14, 2014
Pages 01-
We describe a method of regularization for the restricted Bayesian network BESOM, which has network structure like deep learning. Two types of priors, win-rate penalty and lateral inhibition penalty are introduced to avoid overfitting and local minimum problems.