Recognizing Hand-written Digits Using Hierarchical Products of Experts

The product of experts learning procedure [1] can discover a set of stochastic binary features that constitute a non-linear generative model of handwritten images of digits. The quality of generative models learned in this way can be assessed by learning a separate model for each class of digit and then comparing the unnormalized probabilities of test images under the 10 different class-specific models. To improve discriminative performance, each of the

• Type: Conference
• Year: 2000
• Where: NIPS
• Authors: Guy Mayraz, Geoffrey E. Hinton
• Keywords: Experts Learning Procedure, Generative Models, NIPS 2000, NIPS 2007, Non-linear Generative Model