Alternating Back-Propagation for Generator Network
Abstract
This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back-propagation, which infers the latent factors by Langevin dynamics or gradient descent. (2) Learning back-propagation, which updates the parameters given the inferred latent factors by gradient descent. The gradient computations in both steps are powered by back-propagation, and they share most of their code in common. We show that the alternating back-propagation algorithm can learn realistic generator models of natural images, video sequences, and sounds. Moreover, it can also be used to learn from incomplete or indirect training data.
Cite
@article{arxiv.1606.08571,
title = {Alternating Back-Propagation for Generator Network},
author = {Tian Han and Yang Lu and Song-Chun Zhu and Ying Nian Wu},
journal= {arXiv preprint arXiv:1606.08571},
year = {2016}
}