An adaptive learning method of Restricted Boltzmann Machine by neuron generation and annihilation algorithm
Authors:
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 001273-001278
Abstract
Restricted Boltzmann Machine (RBM) is a generative stochastic energy-based model of artificial neural network for unsupervised learning. Recently, RBM is well known to be a pre-training method of Deep Learning. In addition to visible and hidden neurons, the structure of RBM has a number of parameters such as the weights between neurons and the coefficients for them. Therefore, we may meet some difficulties to determine an optimal network structure to analyze big data. In order to evade the problem, we investigated the variance of parameters to find an optimal structure during learning. For the reason, we should check the variance of parameters to cause the fluctuation for energy function in RBM model. In this paper, we propose the adaptive learning method of RBM that can discover an optimal number of hidden neurons according to the training situation by applying the neuron generation and annihilation algorithm. In this method, a new hidden neuron is generated if the energy function is not still converged and the variance of the parameters is large. Moreover, the inactivated hidden neuron will be annihilated if the neuron does not affect the learning situation. The experimental results for some benchmark data sets were discussed in this paper.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- A Practical Guide to Training Restricted Boltzmann Machines2012
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- Training restricted Boltzmann machines using approximations to the likelihood gradient2008
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- A Learning Algorithm for Boltzmann Machines*Cognitive Science, 1985