Hierarchical IFA Belief Networks

Abstract

We introduce a new real-valued belief network, which is a multilayer generalization of independent factor analysis (IFA). At each level, this network extracts real-valued latent variables that are non-linear functions of the input data with a highly adaptive functional form, resulting in a hierarchical distributed representation of these data. The network is based on a probabilistic generative model, constructed by cascading single-layer IFA models. Whereas exact maximum-likelihood learning for this model is intractable, we present and demonstrate an algorithm that maximizes a lower bound on the likelihood. This algorithm is developed by formulating a variational approach to hierarchical IFA networks.

Cite

Text

Attias. "Hierarchical IFA Belief Networks." Proceedings of the Seventh International Workshop on Artificial Intelligence and Statistics, 1999.

Markdown

[Attias. "Hierarchical IFA Belief Networks." Proceedings of the Seventh International Workshop on Artificial Intelligence and Statistics, 1999.](https://mlanthology.org/aistats/1999/attias1999aistats-hierarchical/)

BibTeX

@inproceedings{attias1999aistats-hierarchical,
  title     = {{Hierarchical IFA Belief Networks}},
  author    = {Attias, Hagai},
  booktitle = {Proceedings of the Seventh International Workshop on Artificial Intelligence and Statistics},
  year      = {1999},
  pages     = {1-9},
  volume    = {R2},
  url       = {https://mlanthology.org/aistats/1999/attias1999aistats-hierarchical/}
}