Meta-aprendizado para otimizacao de parametros de redes neurais

TL;DR

This paper explores using meta-learning to optimize neural network parameters, specifically predicting the ideal number of hidden nodes for MLPs based on problem features, reducing trial-and-error in network design.

Contribution

It introduces a meta-learning approach to select neural network parameters, demonstrated by predicting hidden nodes for MLPs using a meta-dataset of regression problems.

Findings

Meta-learning effectively predicts the optimal number of hidden nodes.

The approach reduces the need for trial-and-error in network configuration.

Results show satisfactory prediction accuracy for new problems.

Abstract

The optimization of Artificial Neural Networks (ANNs) is an important task to the success of using these models in real-world applications. The solutions adopted to this task are expensive in general, involving trial-and-error procedures or expert knowledge which are not always available. In this work, we investigated the use of meta-learning to the optimization of ANNs. Meta-learning is a research field aiming to automatically acquiring knowledge which relates features of the learning problems to the performance of the learning algorithms. The meta-learning techniques were originally proposed and evaluated to the algorithm selection problem and after to the optimization of parameters for Support Vector Machines. However, meta-learning can be adopted as a more general strategy to optimize ANN parameters, which motivates new efforts in this research direction. In the current work, we performed a case study using meta-learning to choose the number of hidden nodes for MLP networks, which is an important parameter to be defined aiming a good networks performance. In our work, we generated a base of meta-examples associated to 93 regression problems. Each meta-example was generated from a regression problem and stored: 16 features describing the problem (e.g., number of attributes and correlation among the problem attributes) and the best number of nodes for this problem, empirically chosen from a range of possible values. This set of meta-examples was given as input to a meta-learner which was able to predict the best number of nodes for new problems based on their features. The experiments performed in this case study revealed satisfactory results.