Hybrid Algorithm for the Optimization of Training Convolutional Neural Network
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2015, Vol 6, Issue 10
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
- EP ID EP106528
- DOI 10.14569/IJACSA.2015.061011
- Views 135
- Downloads 0
Contribution of the Computer Technologies in the Teaching of Physics: Critical Review and Conception of an Interactive Simulation Software
In the present research, we will synthesize the main research results about the development of interactive computer environments for physics teaching and learning. We will see that few types of software propose environme...
RTS/CTS Framework Paradigm and WLAN Qos Provisioning Methods
Wireless local area network (WLAN) communications performance design and management have evolved a lot to be where they are today. They went through some technology’s amendments and innovations. But, some performance too...
Design of a Prediction System for Hydrate Formation in Gas Pipelines using Wireless Sensor Network
Before the evolution of the Wireless Sensor Networks (WSN) technology, many production wells in the oil and gas industry were suffering from the gas hydration formation process, as most of them are remotely located away...
Impact Propagation of Human Errors on Software Requirements Volatility
Requirements volatility (RV) is one of the key risk sources in software development and maintenance projects because of the frequent changes made to the software. Human faults and errors are major factors contributing to...
Efficient Threshold Signature Scheme
In this paper, we introduce a new threshold signature RSA-typed scheme. The proposed scheme has the characteristics of un-forgeable and robustness in random oracle model. Also, signature generation and verificatio...