An Adaptive Learning Method of Restricted Boltzmann Machine by Neuron Generation and Annihilation Algorithm

by   Shin Kamada, et al.

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.


page 1

page 2

page 3

page 4


An Adaptive Learning Method of Deep Belief Network by Layer Generation Algorithm

Deep Belief Network (DBN) has a deep architecture that represents multip...

Highly-scalable stochastic neuron based on Ovonic Threshold Switch (OTS) and its applications in Restricted Boltzmann Machine (RBM)

Interest in Restricted Boltzmann Machine (RBM) is growing as a generativ...

Adaptive Neuron Apoptosis for Accelerating Deep Learning on Large Scale Systems

We present novel techniques to accelerate the convergence of Deep Learni...

Unsupervised prototype learning in an associative-memory network

Unsupervised learning in a generalized Hopfield associative-memory netwo...

Nucleus Neural Network for Super Robust Learning

Artificial neural networks which model the neurons and connecting archit...

Nucleus Neural Network: A Data-driven Self-organized Architecture

Artificial neural networks which are inspired from the learning mechanis...

A topological insight into restricted Boltzmann machines

Restricted Boltzmann Machines (RBMs) and models derived from them have b...

Please sign up or login with your details

Forgot password? Click here to reset