ecms_neu_mini.png

Digital Library

of the European Council for Modelling and Simulation

 

Title:

A Study On Lamarckian And Baldwinian Learning On Noisy And Noiseless Landscapes

Authors:

Cheng Wai Kheng, Meng Hiot Lim, Siang Yew Chong

Published in:

 

(2010).ECMS 2010 Proceedings edited by A Bargiela S A Ali D Crowley E J H Kerckhoffs. European Council for Modeling and Simulation. doi:10.7148/2010 

 

ISBN: 978-0-9564944-1-2

 

24th European Conference on Modelling and Simulation,

Simulation Meets Global Challenges

Kuala Lumpur, June 1-4 2010

 

Citation format:

Kheng, C. W., Lim, M. H., & Chong, S. Y. (2010). A Study On Lamarckian And Baldwinian Learning On Noisy And Noiseless Landscapes. ECMS 2010 Proceedings edited by A Bargiela S A Ali D Crowley E J H Kerckhoffs (pp. 323-329). European Council for Modeling and Simulation. doi:10.7148/2010-0323-0329

DOI:

http://dx.doi.org/10.7148/2010-0323-0329

Abstract:

Lamarckian evolution and Baldwinian effect are two typical replacement schemes of the individual learning process in Memetic Computing. In this paper, we perform a comprehensive study of the behaviour of Lamarckian evolution and Baldwinian effect in noisy and noiseless continuous optimization problems. The output of this study shows that Lamarckian lifetime learning performs better on noiseless problem, while Baldwinian learning performs better on noisy problems.

Full text: