Alternating Back-Propagation for Generator Network
This provides a method for training generative models in machine learning, but it appears incremental as it builds on existing back-propagation techniques.
The paper tackles learning generator network models by proposing an alternating back-propagation algorithm that iterates between inferring latent factors and updating parameters, showing it can learn realistic models for images, videos, and sounds, and handle incomplete or indirect data.
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.