Table of contents
Principle of
DBN Neural Network
Definition of DBN Neural Network Principle of
Restricted Boltzmann Machine (RBM)
Genetic Algorithm Genetic
Algorithm Optimization Deep Belief Network Classification and Identification of DBN
Basic Structure
Main Parameters
Data
MATALB Code
Result Chart
Outlook
back view
DBN is a deep learning neural network, which has the ability to extract features and unsupervised learning. In this paper, DBN is used to extract features. The genetic algorithm has a good global convergence ability. The parameters of DBN are optimized by genetics to realize the complementary strengths of the two.
The principle of DBN neural network
Definition of Deep Belief Neural Network DBN
Deep belief network, DBN, Deep Belief Nets, a kind of neural network. It can be used for unsupervised learning, similar to an autoencoder; it can also be used for supervised learning, as a classifier.
From the perspective of unsupervised learning, the purpose is to preserve the characteristics of the original features as much as possible while reducing the dimensionality of the features. From the perspective of supervised learning, its purpose is to make the classification error rate as small as possible. Whether it is supervised learning or unsupervised learning, the essence of DBN is the process of Feature Learning, that is, how to get better feature expression.
As a neural network, neurons are naturally an essential part of it. DBN consists of several layers of neurons, and the component is a restricted Boltzmann machine (RBM).