• "I want to understand how the brain works, not just from a philosophy perspective, not just in a general way, but in a detailed nuts and bolts mathematical and engineering ways. My desire is not only to understand what intelligence is and how the brain works, but how to build machines that work in the same way. I want to build truly intelligent machines." inspired by J. Hawkins.


  • Representation Learning: If there exsits the unified theory in machine learning, computer vision, and pattern recognition, I believe in that it MUST be representation learning.
    • Trying to explore and understand the mechanism and way of encoding sensory data employing by our brain;
    • Unsupervised and weakly supervised deep learning methods and theoreical analysis such as convergence analysis;
    • Subspace learning, clustering, dimension reduction, manifold learning.
    • Transfer learning, metric learning, etc;
  • Differentiable Programming: The basic idea is to treat neural network as a language to describe the physical variables and their relationships.

Professional Activity:

Leave a Reply