Computer Science – Neural and Evolutionary Computing
Scientific paper
2005-12-09
Computer Science
Neural and Evolutionary Computing
12 pages, 11 figures, journal
Scientific paper
10.1140/epjb/e2006-00137-6
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.
Anastasiadis Aristoklis D.
Magoulas George D.
No associations
LandOfFree
Evolving Stochastic Learning Algorithm Based on Tsallis Entropic Index does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Evolving Stochastic Learning Algorithm Based on Tsallis Entropic Index, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Evolving Stochastic Learning Algorithm Based on Tsallis Entropic Index will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-557146