Structural Optimization of Deep Belief Network by Evolutionary Computation Methods including Tabu Search
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2018, Vol 6, Issue 1
Abstract
This paper proposes structural optimization method of a Deep Belief Network (DBN) which consists of multiple Restricted Boltzmann Machines (RBMs) and a single Feedforward Neural Network (FNN) using several kinds of evolutionary computation methods and modularization. The performance, accuracy of data classification or data prediction, should strongly depend on the structure of the network. Concretely, the number of RMBs, the number of nodes in the hidden layer of RMB. The result of the experiments using some benchmarks for image data classification problems by DBN optimized by the proposed method, DBN without any structural optimization, and some other data classification methods indicate that our proposed method defeats other existing classification methods.
Authors and Affiliations
Tomohiro Hayashida, Ichiro Nishizaki, Shinya Sekizaki, Masanori Nishida, Murman Dwi Prasetio
Keywords
Related Articles
- EP ID EP265776
- DOI 10.14738/tmlai.61.4048
- Views 92
- Downloads 0
Data Cube Representation for patient Diagnosis System Using Fuzzy Object Oriented Database
In the current scenario, everyone wants to store and fetch the information in an easy and faster way. Therefore, the data cube is one of the leading tools in these days that facilitate the user to store and retrieve the...
Identification of Objects by Machines using RFID Technology Identify Objetcs in Internet of Things
Embedded Systems and Internet of Things know recently a revolution in terms of innovation. With connectivity and networks, embedded systems are becoming more communicative, intelligent, and autonomous. They had the abili...
An Objective Approach to Schizophrenia Recognition Utilizing an Adaptive Neuro-Fuzzy Inference (ANFIS) Model
Schizophrenia is a brain disorder that distorts the way a person thinks, acts, expresses emotions, perceives reality, and relates to others. A systematic approach and an overview perception has been carried out over the...
Telecommunications Subscription Fraud Detection using Artificial Neural Networks
Telecommunications Companies are facing a lot of problems due to fraud; hence the need for an effective fraud detection system for the telecommunications companies. This paper presents a design and implements of a subscr...
Nonlinear Time Series Prediction Performance Using Constrained Motion Particle Swarm Optimization
Constrained Motion Particle Swarm Optimization (CMPSO) is a general framework for optimizing Support Vector Regression (SVR) free parameters for nonlinear time series regression and prediction. CMPSO uses Particle Swarm...