Title: Generalizable and Explainable Methods for Learning from Physiological Data and Beyond

Date: April 22, 2024

Time: 3:30 PM - 5:00 PM (EST)

Location: Coda C1103 Lindberg

Zoom Link: https://gatech.zoom.us/j/97333964943?pwd=UEJBQ2MzU2pXZk1RQmRzeGtkYXh2Zz09

Ran Liu

Machine Learning PhD Student

Electrical and Computer Engineering (ECE)
Georgia Institute of Technology

Committee

1 Dr. Eva Dyer (Advisor)

2 Dr. Anqi Wu

3 Dr. Zsolt Kira

4 Dr. Vidya Muthukumar

5 Dr. Vince Calhoun

Abstract

Deep learning (DL) methods have significantly advanced the fields of neuroscience and physiology. However, conventional DL methods that are tailored to specific populations and tasks are no longer adequate in comprehending large-scale, multimodal, and multitask physiological datasets. In this thesis, we propose methods that aim to improve DL methods from the perspective of: (i) Generalizability, enabling applications across diverse modalities, tasks, and subjects, and (ii) Explainability, enabling researchers to understand and potentially customize the learning process to suit specific distributions. These improvements are not only crucial for physiological datasets, which typically require domain knowledge to comprehend, but also improve deep learning methodologies and benefit the broader ML community.