Alternating Back-Propagation for Generator Network

This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a nonlinear 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.

Authors

• Tian Han
• Yang Lu Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China
• Song-Chun Zhu State Key Laboratory of General Artificial Intelligence, BIGAI
• Ying Nian Wu University of California, Los Angeles

Keywords

No keywords are indexed for this paper.