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

Automatic Recognition of Medicinal Plants using Machine Learning Techniques

The proper identification of plant species has major benefits for a wide range of stakeholders ranging from forestry services, botanists, taxonomists, physicians, pharmaceutical laboratories, organisations fighting for e...

HTCSLQ : Hierarchical Tree Congestion Degree with Speed Sending and Sum Costs Link Quality Mechanism for Wireless Sensor Networks

Wireless Sensor Network (wsn) performances have progressed over the last few years, aiming at expanding the lifetime nodes. Among the important studied parts on wsn is the congestion degree that can be identified by seve...

Performance Analysis of Corporate Feed Rectangular Patch Element and Circular Patch Element 4x2 Microstrip Array Antennas

This paper present simple, slim, low cost and high gain circular patch and rectangular patch microstrip array antenna, with the details steps of design process, operate in X-band(8 GHz to 12 GHz) and it provides a mean t...

Deep Learning Approach for Secondary Structure Protein Prediction based on First Level Features Extraction using a Latent CNN Structure

In Bioinformatics, Protein Secondary Structure Prediction (PSSP) has been considered as one of the main challenging tasks in this field. Today, secondary structure protein prediction approaches have been categorized into...

Conceptual Modeling of a Procurement Process

Procurement refers to a process resulting in delivery of goods or services within a set time period. The process includes aspects of purchasing, specifications to be met, and solicitation notifications as in the case of...

Download PDF file
  • EP ID EP106528
  • DOI 10.14569/IJACSA.2015.061011
  • Views 117
  • 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