Neuromorphic Brain-Machine Interface for Improving Attention

Faculty: Prof. Sridharan Devarajan (CNCSA) and Prof. Chetan Singh Thakur (DESE)

Attention is the ability to actively process specific information in the environment while tuning out other details. We are investigating a non-invasive, neuroscience-based approach to enhance attention using neurofeedback. This proposal aims to develop a brain-machine interface (BMI) that improves attention for both healthy individuals and those with attention-related challenges.

The project will involve human brain recordings using techniques like intracranial EEG and functional MRI. In addition to developing novel hardware-optimized, machine learning-based decoder algorithms, our objective includes designing a front-end neuromorphic chip, with the ultimate goal of developing a fully integrated brain-computer interface (BCI) circuit. The system will decode and process brain signals, in real-time using signal processing and machine learning algorithms. The insights and technologies generated through this project could support attention-enhancement applications and lead to effective therapies for children and aging adults with attention disorders.

Over the course of the PhD, the student would get trained in various aspects related to Machine
Learning/Deep Learning, Signal Processing, Cognitive and Computational Neuroscience, Neuromorphic Computing, etc.

Pre-requisites: The ideal candidate should have a background in signal processing, linear algebra, probability, and be proficient in programming (Matlab/Python). The candidate should have an interest in understanding the brain as well as in doing courses on machine learning, deep learning and neuromorphic computing.