Optimizing Deep Neural Network Architecture: A Tabu Search Based Approach

TL;DR

This paper introduces a novel method combining Tabu search and GDM to automatically optimize feedforward neural network architectures, improving their generalization ability for classification tasks.

Contribution

It presents a new hybrid approach that automatically determines optimal FNN architecture parameters using Tabu search combined with GDM training.

Findings

Effective architecture optimization on benchmark datasets

Improved testing error performance

Automated architecture selection process

Abstract

The performance of Feedforward neural network (FNN) fully de-pends upon the selection of architecture and training algorithm. FNN architecture can be tweaked using several parameters, such as the number of hidden layers, number of hidden neurons at each hidden layer and number of connections between layers. There may be exponential combinations for these architectural attributes which may be unmanageable manually, so it requires an algorithm which can automatically design an optimal architecture with high generalization ability. Numerous optimization algorithms have been utilized for FNN architecture determination. This paper proposes a new methodology which can work on the estimation of hidden layers and their respective neurons for FNN. This work combines the advantages of Tabu search (TS) and Gradient descent with momentum backpropagation (GDM) training algorithm to demonstrate how Tabu search can automatically select the best architecture from the populated architectures based on minimum testing error criteria. The proposed approach has been tested on four classification benchmark dataset of different size.