Todd Cao is a deep learning and computer vision practitioner and researcher with broad knowledge of image (object) search, classification and object detection. He is particularly interested in reading and implementing cutting edge research papers to solve real-world problems. Todd is experienced in leading a smaller R&D team to develop an end-to-end training pipeline emphasizing usability, expandability and reproducibility.
Todd’s expertise also includes algorithms and computational geometry. During his PhD, he had created the fastest GPU Euclidean distance transform algorithm that promises an exact result. In his PhD dissertation, he has developed the first series of GPU algorithms to construct several fundamental geometric structures such as convex hull and Delaunay triangulation (with collaborations from a few others). He has also implemented these algorithms with numerical stability and degeneracy tolerance while still achieving orders of magnitude speedup over traditional sequential implementations.