12015104_10153040915857371_6030833281282278467_oI started PhD in Machine Learning under Cambridge-Tübingen PhD Fellowship in the fall 2014, where I am co-supervised by Richard E. Turner and Zoubin Ghahramani at Cambridge, and by Bernhard Schölkopf at the Max Planck Institute for Intelligent Systems in Tübingen. I also collaborate closely with Sergey Levine at UC Berkeley. I completed my B.ASc. in Engineering Science from the University of Toronto, where I did my thesis with Prof. Geoffrey Hinton in distributed training of neural networks using evolutionary algorithms. I also had a great fortune and fun time working with Prof. Steve Mann, developing real-time HDR capture for wearable cameras/displays.  I previously interned at Google Brain, hosted by Ilya Sutskever and Sergey Levine. My PhD is also jointly funded by Facebook and Kenneth-Sutherland Memorial Scholarship. 

I am a member of Jesus College, Cambridge.

Research interests

I am looking into machine learning involving sequential processing, such as sequence learning and reinforcement learning. I am also interested in deep learning, probabilistic models, and generative models.

Publications

  1. Shixiang Gu, Timothy Lillicrap, Ilya Sutskever, Sergey Levine. “Continuous Deep Q-Learning with Model-based Acceleration”. ICML 2016. [Paper]
  2. Shixiang Gu, Sergey Levine, Ilya Sutskever, Andriy Mnih. “MuProp: Unbiased Backpropagation for Stochastic Neural Networks”. ICLR 2016. [Paper]
  3. Shixiang Gu, Zoubin Ghahramani, Richard E. Turner. “Neural Adaptive Sequential Monte Carlo”. NIPS 2015. [Paper] [Supplementary]
  4. Nilesh Tripuraneni*, Shixiang Gu*, Hong Ge, Zoubin Ghahramani. “Particle Gibbs for Infinite Hidden Markov Models”. NIPS 2015. [Paper] *equal contribution
  5. Shixiang Gu, Luca Rigazio. “Toward Deep Neural Network Architectures Robust to Adversarial Examples”. ICLR 2015 Workshop. [Paper]
  6. Steve Mann, Raymond Chun Hing Lo, Kalin Ovtcharov, Shixiang Gu, David Dai, Calvin Ngan, Tao Ai. “Realtime HDR (High Dynamic Range) Video for EyeTap Wearable Computers, FPGA-Based Seeing Aids, and GlassEyes”, IEEE CCECE 2012, Montreal, 2012 April 29 to May 2. 6 pages, to be indexed in IEEE Xplore. ACM SIGGRAPH 2012, Emerging Technologies Exhibition. [Paper] [BibTex] [Video]

Talks

  1. Timothy Lillicrap, Shixiang Gu. “Deep RL methods in Robotics”. Reinforcement Learning Forum. Google, 2016.
  2. Shixiang Gu. “Generalized Backprop, Neural Particle Filter, and Guided Q-Learning”. Research talk hosted by Professor Pieter Abbeel. UC Berkeley, 2015.
  3. Shixiang Gu. “Algorithms for Training Deep Stochastic Neural Networks”. Research talk hosted by Professor Noah Goodman. Stanford University, 2015.
  4. Shixiang Gu, Andrey Malinin. “Long Short-Term Memory Networks”. Machine Learning  RCC. Cambridge University, 2015.

Curriculum vitae

My CV is here.

Contact

Email: sg717 at cam dot ac dot uk
Mail: Office BE4-40, Cambridge University Engineering Department, Trumpington Street, Cambridge CB2 1PZ, UK