Meta-Learning Evolutionary Artificial Neural Networks

TL;DR

This paper introduces MLEANN, a meta-learning framework that automatically optimizes neural network architecture, activation functions, and learning algorithms for improved performance on chaotic time series prediction.

Contribution

The paper presents a novel meta-learning framework, MLEANN, that adaptively optimizes neural network components for better accuracy and efficiency compared to traditional methods.

Findings

MLEANN outperforms conventional neural networks in function approximation.

Different learning algorithms show varied performance depending on network architecture.

MLEANN produces smaller, faster neural networks with superior generalization.

Abstract

In this paper, we present MLEANN (Meta-Learning Evolutionary Artificial Neural Network), an automatic computational framework for the adaptive optimization of artificial neural networks wherein the neural network architecture, activation function, connection weights; learning algorithm and its parameters are adapted according to the problem. We explored the performance of MLEANN and conventionally designed artificial neural networks for function approximation problems. To evaluate the comparative performance, we used three different well-known chaotic time series. We also present the state of the art popular neural network learning algorithms and some experimentation results related to convergence speed and generalization performance. We explored the performance of backpropagation algorithm; conjugate gradient algorithm, quasi-Newton algorithm and Levenberg-Marquardt algorithm for the three chaotic time series. Performances of the different learning algorithms were evaluated when the activation functions and architecture were changed. We further present the theoretical background, algorithm, design strategy and further demonstrate how effective and inevitable is the proposed MLEANN framework to design a neural network, which is smaller, faster and with a better generalization performance.