Title: Using APPM-trained ANN to solve stochastic expected value mode
Authors: Lichao Chen; Lihu Pan; Chunxia Yang
Addresses: School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China ' School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China ' School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China
Abstract: Stochastic expected value model is one classical stochastic optimisation problem. Generally, the fitness function should be constructed and computed with artificial neural network (ANN), thus, the computational efficiency is relied upon the weights and structure of ANN. In this paper, a new algorithm, artificial plant growing process model (APPM) which is inspired by plant growing process, is applied to train the weights of ANN. To show the performance, two examples are chosen to check. Simulation results show it is effective.
Keywords: artificial plant growing process model; process modelling; APPM; stochastic expected value; artificial neural networks; ANNs; stochastic optimisation; simulation.
DOI: 10.1504/IJBIC.2013.055091
International Journal of Bio-Inspired Computation, 2013 Vol.5 No.3, pp.192 - 196
Received: 07 Jan 2013
Accepted: 04 Mar 2013
Published online: 31 Mar 2014 *