On the optimization of convolutional neural networks using bat algorithm

• Grant number: 16/11298-9
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: August 01, 2016
• End date: August 31, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Aparecido Nilceu Marana
• Grantee: Bárbara Caroline Benato
• Supervisor: Xin-She Yang
• Host Institution: Faculdade de Ciências (FC). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil
• Institution abroad: Middlesex University, England
• Associated to the scholarship: 14/12593-9 - Convolution neural networks optimization and its application for facial expression recognition, BP.IC

Abstract

The problem of fine-tuning parameters in deep learning techniques has been considerably focused in the last years, since to hand-tune them is painful and prone to errors. In this proposal, we model the problem of adjusting parameters as an optimization task, since meta- heuristic techniques have obtained very interesting results in a number of problems. There is one inspired on the behavior of microbats that use echolocation to find their prey: the Bat Algorithm (BA) and we decided to evaluate its performance in the context of deep learning-based techniques and for face-based emotion recognition. Additionally, this proposal aims to bring together two research groups from leading universities and to allow an international experience for the student. (AU)