PARTICLE SWARM OPTIMIZATION (PSO) FOR TRAINING OPTIMIZATION ON CONVOLUTIONAL NEURAL NETWORK (CNN)

  • Arie Rachmad Syulistyo Universitas Indonesia, Computer Science Faculty
  • Dwi Marhaendro Jati Purnomo Universitas Indonesia, Computer Science Faculty
  • Muhammad Febrian Rachmadi The University of Edinburgh, School of Informatics
  • Adi Wibowo Nagoya University, Department Micro-Nano System Engineering
Keywords: deep learning, convolutional neural network, particle swarm optimization, deep belief network

Abstract

Neural network attracts plenty of researchers lately. Substantial number of renowned universities have developed neural network for various both academically and industrially applications. Neural network shows considerable performance on various purposes. Nevertheless, for complex applications, neural network’s accuracy significantly deteriorates. To tackle the aforementioned drawback, lot of researches had been undertaken on the improvement of the standard neural network. One of the most promising modifications on standard neural network for complex applications is deep learning method. In this paper, we proposed the utilization of Particle Swarm Optimization (PSO) in Convolutional Neural Networks (CNNs), which is one of the basic methods in deep learning. The use of PSO on the training process aims to optimize the results of the solution vectors on CNN in order to improve the recognition accuracy. The data used in this research is handwritten digit from MNIST. The experiments exhibited that the accuracy can be attained in 4 epoch is 95.08%. This result was better than the conventional CNN and DBN.  The execution time was also almost similar to the conventional CNN. Therefore, the proposed method was a promising method.  

Published
2016-02-15
How to Cite
Syulistyo, A. R., Jati Purnomo, D. M., Rachmadi, M. F., & Wibowo, A. (2016). PARTICLE SWARM OPTIMIZATION (PSO) FOR TRAINING OPTIMIZATION ON CONVOLUTIONAL NEURAL NETWORK (CNN). Jurnal Ilmu Komputer Dan Informasi, 9(1), 52-58. https://doi.org/10.21609/jiki.v9i1.366