Research Article
Reservoir Computing: Size and Connectivity Optimization using the "Worm Algorithm"
|
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
| Volume 69 - Issue 4 |
| Published: May 2013 |
| Authors: A. S. Abdulrasool, S. M. Abbas |
10.5120/11830-7532
|
A. S. Abdulrasool, S. M. Abbas . Reservoir Computing: Size and Connectivity Optimization using the "Worm Algorithm". International Journal of Computer Applications. 69, 4 (May 2013), 18-22. DOI=10.5120/11830-7532
@article{ 10.5120/11830-7532,
author = { A. S. Abdulrasool,S. M. Abbas },
title = { Reservoir Computing: Size and Connectivity Optimization using the "Worm Algorithm" },
journal = { International Journal of Computer Applications },
year = { 2013 },
volume = { 69 },
number = { 4 },
pages = { 18-22 },
doi = { 10.5120/11830-7532 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2013
%A A. S. Abdulrasool
%A S. M. Abbas
%T Reservoir Computing: Size and Connectivity Optimization using the "Worm Algorithm"%T
%J International Journal of Computer Applications
%V 69
%N 4
%P 18-22
%R 10.5120/11830-7532
%I Foundation of Computer Science (FCS), NY, USA
Abstract
This work suggests an algorithm to find the optimum smallest value for Reservoir's Size (RS) and Connectivity Percent (CP) parameters in Reservoir Computing (RC) technique other than the gradient decent and evolutionary computation algorithms. This will help in reducing the required chip area and decreasing the number of multiplications before hardware implementation of RC.
References
- Lukoševi?ius, M. and Jaeger, H. 2009. Reservoir computing approaches to recurrent neural network training. Science Review, vol. 3, pp. 127-149.
- Abdulrasool, A. S. 2010. A Study of Reservoir Computing: Echo State Network and Liquid State Machine. M. Sc. thesis, Electrical Engineering Department, Bghdad University.
- Verstraeten, D. , Schrauwen, B. , D'Haene M. and Stroobandt, D. 2006. The unified Reservoir Computing concept and its digital hardware implementations. In Proceedings of the 2006 EPFL LATSIS Symposium.
- Schrauwen, B. 2008. Towards Applicable Spiking Neural Networks. Doctrine assertion, Gent University of Technology.
- Zurada, J. M. 1992. Introduction to Artificial Neural Systems. West Publishing Company, New York, United States.
- Draper, N. R. and Smith, H. 1998. Applied Regression Analysis, Wiley-Interscience.
- Ishii, K. , Van der Zant, T. , Becanovic, V. and Ploger, P. 2004. Identification of motion with echo state network. OCEANS '04. MTTS/IEEE TECHNO-OCEAN '04 , vol. 3, pp 1205-1210.
- T. Van der Zant, V. Becanavic, K. Ishii, H. Kobiaka, P. Ploeger, "Finding Good Echo State Networks to control an Underwater Robot using Evolutional Computations", In A proceding volume from the 5th IFAC Symposium, 2004.
- Holland, J. H. 1975. Adaptation in natural and artificial systems. The University of Michigan Press, Ann Arbor, MI.
- Rudolph, I. 1991. Global Optimization by means of Distributed Evolutionary Strategies. In: Parallel Problem Solving from Nature, Schwefel, H. P. and Manner, R. Eds. , PPSN, vol. 496 of Lecture Notes in Computer Science, pp 209-213.
- Fujii, T. , Ura T. and Kuroda, Y. 1993. Mlission Execution Experiment with a Newly Develooed AUV the Twin-Burger. In: Proc. of the 8th UUST , pp 92-105.
- Verstraeten, D. , Schrauwen, B. , D'Haene, M. and Stroobandt, D. 2007. An experimental unification of reservoir computing methods. Neural Networks , vol. 29 , pp. 391-403.
- Jaeger, H. 2001. The echo state approach to analyzing and training recurrent neural networks", Technical Report GMD Report 148, German National Research Center for Information Technology.
Index Terms
Keywords