Abubakar, A. and Khan, A. and Nawi, N.M. and Rehman, M.Z. and Teh, Y.W. and Chiroma, H. and Herawan, T. (2016) Studying the Effect of Training Levenberg Marquardt Neural Network by Using Hybrid Meta-Heuristic Algorithms. Journal of Computational and Theoretical Nanoscience, 13 (1). pp. 450-460. ISSN 1546-1955, DOI https://doi.org/10.1166/jctn.2016.4826.
Full text not available from this repository.Abstract
Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt Back propagation (LMBP) still it is not able to avoid local minimum. To deal with this problem, global search optimization technique has the ability to adjust the weight for NN (Neural Network) to avoid the local minima problem. This paper proposes an accelerated particle swarm optimization (APSO) is implemented in conjunction with Levenberg Marquardt back propagation (LMBP) algorithms to achieve faster convergence rate and to avoid local minima problem. The performances of the proposed Accelerated Particle Swarm Optimization Levenberg Marquardt (APSO-LM) algorithms compared by means of simulations on 7-Bit Parity and six UCI benchmark classification datasets. The simulation results show that the APSO-LM algorithm shows better performance than baseline algorithms in terms of convergence speed and Mean Squared Error (MSE).
| Item Type: | Article |
|---|---|
| Funders: | UNSPECIFIED |
| Uncontrolled Keywords: | Data Classification; Levenberg Marquardt Back Propagation; Local Minima; Nature Inspired Algorithms; Particle Swarm Optimization |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Computer Science & Information Technology |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 23 Oct 2017 01:49 |
| Last Modified: | 23 Oct 2017 01:49 |
| URI: | http://eprints.um.edu.my/id/eprint/18033 |
Actions (login required)
 |
View Item |
