Improving Pre-Trained Weights Through Meta-Heuristics Fine-Tuning

TL;DR

This paper explores using bio-inspired meta-heuristic algorithms to fine-tune pre-trained neural network weights, aiming to escape local optima and enhance performance across image and text classification tasks.

Contribution

It introduces a novel approach of applying meta-heuristics for fine-tuning pre-trained weights, demonstrating improved results over traditional methods.

Findings

Meta-heuristics outperform baseline pre-trained models.

Enhanced exploration leads to better classification accuracy.

Analysis identifies critical weights for fine-tuning.

Abstract

Machine Learning algorithms have been extensively researched throughout the last decade, leading to unprecedented advances in a broad range of applications, such as image classification and reconstruction, object recognition, and text categorization. Nonetheless, most Machine Learning algorithms are trained via derivative-based optimizers, such as the Stochastic Gradient Descent, leading to possible local optimum entrapments and inhibiting them from achieving proper performances. A bio-inspired alternative to traditional optimization techniques, denoted as meta-heuristic, has received significant attention due to its simplicity and ability to avoid local optimums imprisonment. In this work, we propose to use meta-heuristic techniques to fine-tune pre-trained weights, exploring additional regions of the search space, and improving their effectiveness. The experimental evaluation comprises two classification tasks (image and text) and is assessed under four literature datasets. Experimental results show nature-inspired algorithms' capacity in exploring the neighborhood of pre-trained weights, achieving superior results than their counterpart pre-trained architectures. Additionally, a thorough analysis of distinct architectures, such as Multi-Layer Perceptron and Recurrent Neural Networks, attempts to visualize and provide more precise insights into the most critical weights to be fine-tuned in the learning process.