Research

At the Learning and Inference Lab, we study how learning systems can extract reliable and informative structure from complex, high-dimensional, time series, noisy, and multimodal data. Our research lies at the intersection of machine learning, information theory, and statistical signal processing, with a focus on representation learning, multimodal learning, probabilistic machine learning, generative models, and time series analysis. We aim to build ML systems that are not only accurate, but also theoretically grounded, interpretable, and robust. 

Core Areas (but not limited to):

• Multimodal & Representation Learning

• Probabilistic Machine Learning / Generative Models

• Statistical Signal Processing & Information Theory

• Times Series Analysis

• ML and Statistical Methods for Bio/Medical and Semi-conductor

Mathematical Backgrounds: Probability & Statistics, Linear Algebra, Random Process, Algorithms, Machine Learning, and Optimizations