Our research addresses fundamental problems in developing biologically plausible machine/deep learning algorithms for various applications including medical/computer vision, brain-computer interfaces, healthcare, and neuroinformatics.

• We aim to develop novel deep learning methods that can integrate multiple neuroimaging modalities, e.g., MRI, PET, fMRI, and genetic data, so that we maximally utilize the complimentary information inherent in different modalities, and are also interested in devising computational models for an expert system of brain disorder diagnosis or prognosis including Alzheimer’s Disease (AD) and its prodromal stage Mild Cognitive Impairment (MCI), Autism Spectral Disorder (ASD), and Major Depressive Disorder (MDD).
• We develop various applications for medical/computer vision tasks, where the objective is to achieve state-of-the-art performance with human-level interpretability in mind. Few of our main research topics include, but not limited to, recognition, detection, classification, segmentation, synthesis, captioning, and VQA in medical (MRI, PET, CT, and etc.) and computer (natural, facial, industrial, and etc.) vision tasks.
• We develop BCI-oriented but paradigm-independent algorithms that intelligently remove artifacts/noise and learn user-specific brain signal patterns by utilizing their resting-state signals.
• We develop deep architectures for disease phenotyping, future patients’ state prediction, missing value imputation, and uncertainty quantification from Electronic Health Records (EHR) for better understanding and investigation of the underpinning phenomena in healthcare observations.
• We develop machine-learning algorithms that can estimate the underlying functional patterns from fMRI images and utilize the estimated information for disease diagnosis/prognosis.