Title: Training artificial neural networks using APPM

Authors: Zhihua Cui; Chunxia Yang; Sugata Sanyal

Addresses: Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, Shanxi, 030024, China; State Key Laboratory of Novel Software Technology, Nanjing University, 210093, China. ' Complex System and Computational Intelligence Laboratory, Taiyuan University of Science and Technology, Shanxi, 030024, China. ' School of Technology & Computer Science, Tata Institute of Fundamental Research, Homi Bhabha Road, Mumbai-400005, India

Abstract: In order to train Artificial Neural Networks (ANNs), we used a new stochastic optimisation algorithm that simulates the plant growing process. It designs an artificial photosynthesis operator and an artificial phototropism operator to mimic photosynthesis and phototropism mechanisms, we call it briefly APPM algorithm. In this algorithm, each individual is called a branch, and the sampled points are regarded as the branch growing trajectory. Phototropism operator is designed to introduce the fitness function value, and it is also used to decide the growing direction. In this paper, we apply APPM algorithm to train the connection weights for ANN. To assess the performance of our APPM-trained ANN (APPMANN), two real-world problems, named Cleveland heart disease classification problem and sunspot number forecasting problem, are adopted. Simulation results show that APPMANN increases the performance significantly when compared with other sophisticated machine learning techniques proposed in recent years.

Keywords: photosynthesis operators; phototropism operators; artificial neural networks; ANNs; training; stochastic optimisation; simulation; plant growth; branch growing; heart disease classification; sunspot number forecasting; machine learning.

DOI: 10.1504/IJWMC.2012.046787

International Journal of Wireless and Mobile Computing, 2012 Vol.5 No.2, pp.168 - 174

Received: 09 Jan 2012
Accepted: 11 Feb 2012
Published online: 11 Jan 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article