Biogeography-Based Optimization for Weight Optimization in Elman Neural Network Compared with Meta-Heuristics Methods

Habib Dhahri

Abstract


In this paper, we present a learning algorithm for the Elman Recurrent Neural Network (ERNN) based on Biogeography-Based Optimization (BBO). The proposed algorithm computes the weights, initials inputs of the context units and self-feedback coefficient of the Elman network. The method applied for four benchmark problems: Mackey Glass and Lorentz equations, which produce chaotic time series, and to real life classification; iris and Breast Cancer datasets. Numerical experimental results show improvement of the performance of the proposed algorithm in terms of accuracy and MSE eror over many heuristic algorithms.

Keywords


Biogeography-Based Optimization; Time series predictions; classification

Full Text:

VIEW PDF


DOI: http://dx.doi.org/10.18662/brain/11.2/76

From Writerra Research

(C) 2010-2019 EduSoft