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 127
- Downloads 0
Design and Analysis of DNA Encryption and Decryption Technique based on Asymmetric Cryptography System
Security of sensitive information at the time of transmission over public channels is one of the critical issues in digital society. The DNA-based cryptography technique is a new paradigm in the cryptography field that i...
Optimizing the Hyperparameter of Feature Extraction and Machine Learning Classification Algorithms
The process of assigning a quantitative value to a piece of text expressing a mood or effect is called Sentiment analysis. Comparison of several machine learning, feature extraction approaches, and parameter optimization...
Forecasting Production Values using Fuzzy Logic Interval based Partitioning in Different Intervals
Fuzzy time series models have been put forward for rice production from many researchers around the globe, but the prediction has not been very accurate. Frequency density or ratio based partitioning methods have been us...
Evaluation of the Performance of the University Information Systems: Case of Moroccan Universities
The purpose of this paper is to develop a conceptual model of university information systems performance measurement. To do this resorted to the choice of 3E-3P model. This model proposes a development under the spectrum...
A new optimization based image segmentation method by particle swarm optimization
This paper proposes a new multilevel thresholding method segmenting images based on particle swarm optimization (PSO). In the proposed method, the thresholding problem is treated as an optimization problem, and sol...