Combining euclidean and riemannian alignment for transfer learning in the brain-computer interfaces

• Grant number: 23/06407-7
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: September 01, 2023
• End date: December 31, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Raphael Yokoingawa de Camargo
• Grantee: Bruna Junqueira de Almeida Ferreira Lopes
• Supervisor: Sylvain Chevallier
• Host Institution: Centro de Matemática, Computação e Cognição (CMCC). Universidade Federal do ABC (UFABC). Ministério da Educação (Brasil). Santo André , SP, Brazil
• Institution abroad: Laboratoire Interdisciplinaire des Sciences du Numérique, Gif-sur-Yvette (LISN), France
• Associated to the scholarship: 22/08920-0 - Ensemble deep learning for transfer learning in brain-computer interface, BP.IC

Abstract

Riemannian Alignment (RA) techniques are considered state-of-the-art methods for transfer learning between subjects in the brain-computer interface (BCI) motor imagery paradigm. In the current fellowship, we showed that Euclidean alignment (EA) techniques enable efficient transfer learning between subjects using Deep Learning models. In this internship project, we will compare transfer learning performance using EA and RA techniques and evaluate ways to combine these alignment techniques to improve transfer learning using Deep Learning models. (AU)