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

by   Shin Kamada, et al.
Prefectural University of Hiroshima

Deep Belief Network (DBN) has a deep architecture that represents multiple features of input patterns hierarchically with the pre-trained Restricted Boltzmann Machines (RBM). A traditional RBM or DBN model cannot change its network structure during the learning phase. Our proposed adaptive learning method can discover the optimal number of hidden neurons and weights and/or layers according to the input space. The model is an important method to take account of the computational cost and the model stability. The regularities to hold the sparse structure of network is considerable problem, since the extraction of explicit knowledge from the trained network should be required. In our previous research, we have developed the hybrid method of adaptive structural learning method of RBM and Learning Forgetting method to the trained RBM. In this paper, we propose the adaptive learning method of DBN that can determine the optimal number of layers during the learning. We evaluated our proposed model on some benchmark data sets.


page 1

page 2

page 3

page 4


Adaptive Learning Method of Recurrent Temporal Deep Belief Network to Analyze Time Series Data

Deep Learning has the hierarchical network architecture to represent the...

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

Restricted Boltzmann Machine (RBM) is a generative stochastic energy-bas...

Automatic Extraction of Road Networks from Satellite Images by using Adaptive Structural Deep Belief Network

In our research, an adaptive structural learning method of Restricted Bo...

Fine Tuning Method by using Knowledge Acquisition from Deep Belief Network

We developed an adaptive structure learning method of Restricted Boltzma...

Please sign up or login with your details

Forgot password? Click here to reset