Training feedforward neural networks using hybrid flower pollination-gravitational search algorithm

Dwaipayan Chakraborty, Sankhadip Saha, Samaresh Maity

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Scopus citations

Abstract

Error minimization using conventional back-propagation algorithm for training feed forward neural network (FNN) suffers from problems like slow convergence and local minima trap. Here in this paper gradient free optimization is used for error minimization to avoid local minima. Hence we introduce a new hybrid algorithm integrating the concepts of physics inspired gravitational search algorithm and biology inspired flower pollination algorithm. Gravitational search algorithm is a novel meta-heuristic optimization method based on the Newtonian law of gravity and mass interaction, whereas flower pollination algorithm is an intriguing process based on the pollination characteristics of flowering plants. Gravitational search algorithm efficiently evaluates global optimum but it suffers from slow searching speed in the last iterations. Flower pollination algorithm exhibits faster searching but suffers from local minima due to the switch probability. Experimental results show that hybrid FP-GSA outperforms both FPA and GSA for training FNNs in terms of classification accuracy.

Original languageEnglish (US)
Title of host publication2015 1st International Conference on Futuristic Trends in Computational Analysis and Knowledge Management, ABLAZE 2015
EditorsBhawna Kumar, Gurinder Singh, J.S. Jassi
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages261-266
Number of pages6
ISBN (Electronic)9781479984336
DOIs
StatePublished - Jul 10 2015
Externally publishedYes
Event2015 1st International Conference On Futuristic Trends in Computational Analysis and Knowledge Management, ABLAZE 2015 - Greater Noida, India
Duration: Feb 25 2015Feb 27 2015

Publication series

Name2015 1st International Conference on Futuristic Trends in Computational Analysis and Knowledge Management, ABLAZE 2015

Conference

Conference2015 1st International Conference On Futuristic Trends in Computational Analysis and Knowledge Management, ABLAZE 2015
Country/TerritoryIndia
CityGreater Noida
Period2/25/152/27/15

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Training feedforward neural networks using hybrid flower pollination-gravitational search algorithm'. Together they form a unique fingerprint.

Cite this