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 85
- Downloads 0
Fuzzy Rough Classification Models for Network Intrusion Detection
In recent years advancements in communication technology have led to a wide range of Internet services. While an overwhelming number of Internet users have shown interest in such services, incidences of cyber-attacks by...
Functional Implementation of Multiple Traversals Program with Attribute Grammars in Scala
Attribute grammars are a powerful specification paradigm for many language processing tasks, particularly the semantic analysis of programming languages. To functionally evaluate attributes grammar in Scala, the studies...
Automatic Tool Selection System based on STEP_NC and ISO13399 Standards
Computer Aided Process Planning (CAPP) is considered as an essential component of Computer Integrated manufacturing (CIM) environment and it is an important interface between Computer Aided Design (CAD) and Computer Aide...
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...
Contextual Arabic Handwriting Recognition System Using Embedded Training Based Hybrid HMM/MLP Models
Recognizing unconstrained cursive Arabic handwritten text is a very challenging task the use of hybrid classification to take advantage of the strong modeling of Hidden Markov Models (HMM) and the large capacity of discr...