Evolving Stochastic Learning Algorithm Based on Tsallis Entropic Index

TL;DR

This paper introduces a novel evolving stochastic learning algorithm for neural networks that leverages Tsallis entropy, combining deterministic and stochastic methods with adaptive stepsizes, improving convergence speed and stability.

Contribution

The paper presents a new learning algorithm based on Tsallis statistical mechanics that adaptively balances stochastic and deterministic search for neural network training.

Findings

Faster convergence compared to previous schemes

Influence of entropic index q on learning behavior

Temperature T affects stochasticity and stability

Abstract

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.