Constructing Hierarchical Bayesian Networks With Pooling

Authors

  • Kaneharu Nishino The University of Tokyo
  • Mary Inaba The University of Tokyo

Keywords:

Machine Learning, Pattern Recognition, Bayesian Network, Bayesian Brain Hypothesis

Abstract

Inspired by the Bayesian brain hypothesis and deep learning, we develop a Bayesian autoencoder, a method of constructing recognition systems using a Bayesian network. We construct hierarchical Bayesian networks based on feature extraction and implement pooling to achieve invariance within a Bayesian network framework. The constructed networks propagate information bidirectionally between layers. We expect they will be able to achieve brain-like recognition using local features and global information such as their environments.

Downloads

Published

2018-04-29

How to Cite

Nishino, K., & Inaba, M. (2018). Constructing Hierarchical Bayesian Networks With Pooling. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12191