论文信息 - Discriminative Restricted Boltzmann Machines are Universal Approximators for Discrete Data

Discriminative Restricted Boltzmann Machines are Universal Approximators for Discrete Data

This report proofs that discriminative Restricted Boltzmann Machines (RBMs) are universal approximators for discrete data by adapting existing universal approximation proofs for generative RBMs. Discriminative Restricted Boltzmann Machines are Universal Approximators for Discrete Data Laurens van der Maaten Pattern Recognition & Bioinformatics Laboratory Delft University of Technology

L. V. D. Maaten | L. Maaten

[1] Yoshua Bengio,et al. Classification using discriminative restricted Boltzmann machines , 2008, ICML '08.

[2] Nicolas Le Roux,et al. Representational Power of Restricted Boltzmann Machines and Deep Belief Networks , 2008, Neural Computation.

[3] David Haussler,et al. Unsupervised learning of distributions on binary vectors using two layer networks , 1991, NIPS 1991.