Hung Ngo

• Ph.D. student (2010-2014) under the supervision of Professor Jürgen Schmidhuber and Dr. Alexander Forster at IDSIA (Dalle Molle Institute for Artificial Intelligence), USI-SUPSI, Manno-Lugano, Switzerland.
• M.S. (highest honors) in Computer Science (March 2005), KyungHee University, Korea.
• B.E. (highest honors) in Electronics and Telecommunications (March 2003), HCMC University of Technology, HCMC, Vietnam

I am broadly interested in interactive machine learning and artificial curiosity. This includes aspects of online active learning, hierarchical reinforcement learning, deep unsupervised learning, with applications in autonomous developmental robots, computer vision, and natural language processing.

• 04/05/2014: Our paper on Approximate Planning for Bayesian Hierarchical Reinforcement Learning is accepted for publication in Applied Intelligence journal!
• 30/01/2014: Our journal paper entitled Efficient Interactive Multiclass Learning from Binary Feedback will appear in the 2014 Special Issue on Machine Learning for Multiple Modalities in Interactive Systems and Robots!
• 19/12/2013: Our video submission has been accepted at HRI 2014, on Fast, Interactive Learning from Binary Feedback for Human-Robot Cooperation (joint first authors with Jawad Nagi).
• 19/12/2013: Our paper has been accepted at AAMAS 2014, on Monte Carlo Bayesian Hierarchical Reinforcement Learning (joint work with Vien Ngo).
• 10/12/2013: My thesis committee (including Profs. Pierre-Yves Oudeyer, Marco Wiering, Marc Langheinrich, and Kai Hormann) has been approved by the faculty!
• 26/11/2013: Our Frontiers journal paper on Self-generated Exploration Goals has been published online (and open access)!
• 22/11/2013: I was back from the very exciting 2013 HRI Autumn School at TU Dresden!
• 15/10/2013: Our paper has been accepted at CCNC 2014, on Location-based Data Dissemination with Human Mobility Using Online Density Estimation (joint work with Duc Le).

(For a complete list, see my publication page. See also my Google Scholar page.)

• V. Ngo, H. Ngo, S.Y. Lee, T.C. Chung. Approximate Planning for Bayesian Hierarchical Reinforcement Learning. Journal of Applied Intelligence, 2014.
• H. Ngo, M. Luciw, V. Ngo, J. Nagi, A. Forster, J. Schmidhuber. Efficient Interactive Multiclass Learning from Binary Feedback. ACM Trans. on Interactive Intelligent Systems, 2014. (PDF, Video demos)
• H. Ngo, M. Luciw, A. Forster, J. Schmidhuber. Confidence-Based Progress-Driven Self-Generated Goals for Skill Acquisition in Developmental Robots. Frontiers in Cognitive Science Journal, Oct. 2013. (PDF, Video demos)
• H. Ngo, M. Luciw, V. Ngo, J. Schmidhuber. Upper Confidence Weighted Learning for Efficient Exploration in Multiclass Prediction with Binary Feedback. IJCAI 2013, Beijing, China. (PDF)
• H. Ngo, M. Luciw, A. Forster, J. Schmidhuber. Learning Skills from Play: Artificial Curiosity on a Katana Robot Arm. IJCNN 2012, Brisbane, Australia. (IM-CLeVeR project page, PDF, Video demos)
• H. Ngo, M. Ring, J. Schmidhuber. Compression Progress-based Curiosity Drive for Developmental Learning. ICDL-EpiRob 2011, Frankfurt, Germany. (PDF)
• Hung Ngo, S.Y. Lee, Y.K.Lee. Factor Graph Approach to Distributed Facility Location in Large-Scale Networks. IEEE International Symposium on Information Theory, ISIT 2009, Seoul, Korea (PDF)

• Deep learning of behavioral hierarchy for autonomous visual navigation: On-going work, applying deep RL directly on images from onboard camera to learn robotic skills for navigation. The novelty of our approach lies in the mechanism of self-generating goals, which exploits the environment structure and regularities through a deep hierarchical temporal coherence network.
• Efficient multiclass prediction from binary feedback, HRI demo on footbot for hand gesture-based interactive learning from binary feedback, Nov. 2013.
• Toward intelligent humanoids, IM-CLeVeR project demo 2012.
• Curious Katana arm learns from play, IJCNN2012. See also this short, "high-impact" demo!

Available soon ...

IDSIA
Galleria 2, CH-6928 Manno-Lugano, Ticino - Switzerland
Tel: +41 (0)58 666 6717

Last modified June 5th, 2014.