Summary
Bernard Ng is a Research Assistant Professor with 14 years of experience developing statistical and machine learning methods for biomedical data, with deep expertise in sparse Gaussian graphical models, Riemannian statistics, and multi-omic integration. His work spans fMRI connectivity, genetics and genomics, and large-scale molecular QTL analyses, and he has a track record of improving sensitivity and interpretability in brain imaging and multimodal studies. He has advanced methods for integrating imaging and diffusion data, devised sparse models for common connectivity patterns, and proposed multi-omic approaches that link GWAS regulatory variants to disease genes. Currently he combines deep learning for sequence-to-expression prediction with models that associate gene variation to brain connectomes, aiming to bridge genome, epigenome, transcriptome, connectome, and phenome. Based in Greater Vancouver, he pairs rigorous PhD-level statistical training with hands-on neuroimaging and genomics collaborations across top institutions, often prioritizing biologically informed priors to boost real-world robustness.
14 years of coding experience
16 years of employment as a software developer
Doctor of Philosophy, Electrical and Computer Engineering, Doctor of Philosophy, Electrical and Computer Engineering at The University of British Columbia / UBC
Bachelor of Applied Science, Electronics Engineering, Bachelor of Applied Science, Electronics Engineering at Simon Fraser University
English, Chinese, Japanese