My researches aim at 1) developing Differentiable/ Meta/ Reinforcement Learning algorithms that endow machines and devices to solve complex tasks with larger autonomy, 2) understanding foundations of deep learning algorithms, and 3) enabling applications in Computer Vision and Artificial Intelligence such as Neural Architecture Search, 3D Vision, Scene and Video Understanding. Biography
and AI Blog
Research Topics and Popular Benchmarks. See Publication List for more details.
Meta-learning to learn normalization method for each hidden layer in ConvNet.
Presentations, Tutorials, and Workshops