Learning Generative Models with the Up Propagation Algorithm

Part of Advances in Neural Information Processing Systems 10 (NIPS 1997)

Authors

Jong-Hoon Oh, H. Sebastian Seung

Abstract

Up-propagation is an algorithm for inverting and learning neural network generative models Sensory input is processed by inverting a model that generates patterns from hidden variables using topdown connections The inversion process is iterative utilizing a negative feedback loop that depends on an error signal propagated by bottomup connections The error signal is also used to learn the generative model from examples The algorithm is benchmarked against principal component analysis in experiments on images of handwritten digits.