Anastasiadis, A.D. and Magoulas, George D. (2006) Evolving stochastic learning algorithm based on Tsallis entropic index. The European Physical Journal B - Condensed Matter and Complex Systems 50 (1-2), pp. 277-283. ISSN 1434-6028.
Download (263kB) | Preview
In this paper, inspired from our previous algorithm, which was based on the theory of Tsallis statistical mechanics, we develop a new evolving stochastic learning algorithm for neural networks. The new algorithm combines deterministic and stochastic search steps by employing a different adaptive stepsize for each network weight, and applies a form of noise that is characterized by the nonextensive entropic index q, regulated by a weight decay term. The behavior of the learning algorithm can be made more stochastic or deterministic depending on the trade off between the temperature T and the q values. This is achieved by introducing a formula that defines a time-dependent relationship between these two important learning parameters. Our experimental study verifies that there are indeed improvements in the convergence speed of this new evolving stochastic learning algorithm, which makes learning faster than using the original Hybrid Learning Scheme (HLS). In addition, experiments are conducted to explore the influence of the entropic index q and temperature T on the convergence speed and stability of the proposed method.
|Additional Information:||Copyright © EDP Sciences, Società Italiana di Fisica, Springer-Verlag 2006. The original publication is available at www.springerlink.com|
|School:||Birkbeck Schools and Research Centres > School of Business, Economics & Informatics > Computer Science and Information Systems|
|Research Centre:||Birkbeck Knowledge Lab|
|Depositing User:||Sandra Plummer|
|Date Deposited:||11 Jun 2007|
|Last Modified:||02 Dec 2016 13:23|
Archive Staff Only (login required)