Hybrid Algorithm for the Optimization of Training Convolutional Neural Network

Abstract

The training optimization processes and efficient fast classification are vital elements in the development of a convolution neural network (CNN). Although stochastic gradient descend (SGD) is a Prevalence algorithm used by many researchers for the optimization of training CNNs, it has vast limitations. In this paper, it is endeavor to diminish and tackle drawbacks inherited from SGD by proposing an alternate algorithm for CNN training optimization. A hybrid of genetic algorithm (GA) and particle swarm optimization (PSO) is deployed in this work. In addition to SGD, PSO and genetic algorithm (PSO-GA) are also incorporated as a combined and efficient mechanism in achieving non trivial solutions. The proposed unified method achieves state-of-the-art classification results on the different challenge benchmark datasets such as MNIST, CIFAR-10, and SVHN. Experimental results showed that the results outperform and achieve superior results to most contemporary approaches.

Authors and Affiliations

Hayder Albeahdili, Tony Han, Naz Islam

Keywords

Related Articles

Introducing a Method for Modeling Knowledge Bases in Expert Systems Using the Example of Large Software Development Projects

Goal of this paper is to develop a meta-model, which provides the basis for developing highly scalable artificial intelligence systems that should be able to make autonomously decisions based on different dynamic and spe...

Facial Expression Recognition using Hybrid Texture Features based Ensemble Classifier

Communication is fundamental to humans. In the literature, it has been shown through many scientific research studies that human communication ranges from 54 to 94 percent is non-verbal. Facial expressions are the most o...

Omega Model for Human Detection and Counting for application in Smart Surveillance System

Driven by the significant advancements in technology and social issues such as security management, there is a strong need for Smart Surveillance System in our society today. One of the key features of a Smart Surveillan...

On Standards for Application Level Interfaces in SDN

In this paper, authors discuss application level interfaces for Software Defined Networks. While the Application Programming Interfaces for the interaction with the hardware are widely described in Software Defined Netwo...

A Decision Support Tool for Inferring Further Education Desires of Youth in Sri Lanka

This paper presents the results of a study carried out to identify the factors that influence the further education desires of Sri Lankan youth. Statistical modeling has been initially used to infer the desires of the yo...

Download PDF file
  • EP ID EP106528
  • DOI 10.14569/IJACSA.2015.061011
  • Views 120
  • Downloads 0

How To Cite

Hayder Albeahdili, Tony Han, Naz Islam (2015). Hybrid Algorithm for the Optimization of Training Convolutional Neural Network. International Journal of Advanced Computer Science & Applications, 6(10), 79-85. https://europub.co.uk/articles/-A-106528