To Be Bernoulli or to Be Gaussian, for a Restricted Boltzmann Machine.

Takayoshi Yamashita Masayuki Tanaka Eiji Yoshida Yuji Yamauchi Hironobu Fujiyoshi

Published in: ICPR (2014)

Keyphrases

restricted boltzmann machine
deep learning
probabilistic graphical models
learning algorithm
conditional random fields
semi supervised
neural network
loopy belief propagation
information retrieval
training data
information extraction
markov networks