Deep learning and brain-computer interfaces

• Grant number: 18/04100-3
• Support Opportunities: Scholarships in Brazil - Master
• Start date: July 01, 2018
• End date: August 31, 2019
• Field of knowledge: Engineering - Electrical Engineering - Telecommunications
• Agreement: Coordination of Improvement of Higher Education Personnel (CAPES)
• Principal Investigator: Romis Ribeiro de Faissol Attux
• Grantee: Willian Rampazzo
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 13/07559-3 - BRAINN - The Brazilian Institute of Neuroscience and Neurotechnology, AP.CEPID

Abstract

Neural networks are part of a well-established research field within the broad subject of machine learning. In the last years, this field has received a great deal of attention due to the growing interest in deep neural networks (DNNs). These networks have a structure characterized by the presence of several processing layers, which are responsible for a feature extraction process that, ideally, avoids the need for feature engineering. The approach has proven itself extremely relevant in fields as distinct as image recognition and automated text translation.In this project, we will propose DNNs that perform, using raw eletroencephalography data, the classification task inherent to a brain-computer interface (BCI). BCIs based on evoked potentials and motor imagery will be considered. The results will be compared to those obtained with classical BCIs, which treat the processes of feature extraction and classification in separate. (AU)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

RAMPAZZO, Willian. Deep learning and brain-computer interfaces. 2019. Master's Dissertation - Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação Campinas, SP.