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

Author(s)

de Rosa, Gustavo H. ; Roder, Mateus ; Papa, Joao Paulo ; dos Santos, Claudio F. G. ; IEEE

• Document type: Journal article
• Source: 2021 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2021); v. N/A, p. 8-pg., 2021-01-01.

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. (AU)

• FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
• Grantee: Francisco Louzada Neto
• Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC
• FAPESP's process: 19/07665-4 - Center for Artificial Intelligence
• Grantee: Fabio Gagliardi Cozman
• Support Opportunities: Research Grants - Research Program in eScience and Data Science - Research Centers in Engineering Program
• FAPESP's process: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?
• Grantee: Alexandre Xavier Falcão
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 19/02205-5 - Adversarial learning in natural language processing
• Grantee: Gustavo Henrique de Rosa
• Support Opportunities: Scholarships in Brazil - Doctorate
• FAPESP's process: 20/12101-0 - Support for computational environments and experiments execution: data acquisition, categorization and maintenance
• Grantee: Leandro Aparecido Passos Junior
• Support Opportunities: Scholarships in Brazil - Technical Training Program - Technical Training