Email: image text

About Me

I got my PhD from the Department of Computer Science of the University of Maryland, College Park in summer 2016. I work at Facebook now.
My main interest is in neural networks and artificial intelligence in general, with the overall goal being to advance our understanding of and make progress towards "strong AI". Specifically, I am interested in studying what computations can be achieved by incorporating biological inspirations, how complex global behaviors/computations can emerge from simple local rules, and how the above computational principles can be engineered towards creating useful machine intelligence.
My dissertation research, advised by Jim Reggia, was about self-organizing map neural architectures based on limit cycle dynamics. In parallel, I also worked on an ONR project studying effective imitation learning for robots. In an independent project earlier, I studied large-scale genetic algorithms using cloud computing methods.
I have a passion for programming.
I used to work on wireless mesh networks while I was a graduate student in National Taiwan University.

Software

SMILE is an open-source simulated 3D environment supporting studies in robot imitation learning, based on our virtual demonstrator hypothesis. See project page and publications for details.
.NET RTF Writer Library in C#, as its name suggests, is a .NET library that client code can call to generate Rich Text Format (RTF) documents. The generated documents can be viewed and edited in Microsoft Word or other editors supporting RTF. This project is pretty old and has been discontinued.

Publications

Journals

  1. Huang, D.-W., Gentili, R., Katz, G., & Reggia, J. (2017). A limit-cycle self-organizing map architecture for stable arm control. Neural Networks, 85, 165–181. PDF | Supplemental | Video
  2. Katz, G., Huang, D.-W., Hauge, T., Gentili, R., & Reggia, J. (2017). A novel parsimonious cause-effect reasoning algorithm for robot imitation and plan recognition. IEEE Transactions on Cognitive and Developmental Systems, 10(2), 177–193.
  3. Reggia, J., Huang, D.-W., & Katz, G. (2017). Exploring the computational explanatory gap. Philosophies, 2(1), 5.
  4. Reggia, J., Katz, G., & Huang, D.-W. (2016). What are the computational correlates of consciousness? Biologically Inspired Cognitive Architectures, 17, 101–113.
  5. Huang, D.-W., Gentili, R., & Reggia, J. (2015). Self-organizing maps based on limit cycle attractors. Neural Networks, 63, 208–222. PDF
  6. Gentili, R., Oh, H., Huang, D.-W., Katz, G., Miller, R., & Reggia, J. (2015). A neural architecture for performing actual and mentally simulated movements during self-intended and observed bimanual arm reaching movements. International Journal of Social Robotics, 7(3), 371–392.
  7. Reggia, J., Huang, D.-W., & Katz, G. (2015). Beliefs concerning the nature of consciousness. Journal of Consciousness Studies, 22(5-6), 146–171.
  8. Huang, D.-W., Lin, P., & Gan, C.-H. (2008). Design and performance study for a mobility management mechanism (WMM) using location cache for wireless mesh networks. IEEE Transactions on Mobile Computing, 7(5), 546–556. PDF
  9. Guizani, M., Lin, P., Cheng, S.-M., Huang, D.-W., & Fu, H.-L. (2008). Performance evaluation for minislot allocation for wireless mesh networks. IEEE Transactions on Vehicular Technology, 57(6), 3732–3745.

Conferences

  1. Katz, G., Huang, D.-W., Gentili, R., & Reggia, J. (2017). An Empirical Characterization of Parsimonious Intention Inference for Cognitive-Level Imitation Learning. In International Conference on Artificial Intelligence (ICAI).
  2. Reggia, J., Katz, G., & Huang, D.-W. (2016). What are the computational correlates of consciousness? In International Conference on Biologically Inspired Cognitive Architectures (BICA).
  3. Katz, G., Huang, D.-W., Gentili, R., & Reggia, J. (2016). Imitation learning as cause-effect reasoning. In Steunebrink, B., Wang, P., & Goertzel, B. (Eds.), Artificial General Intelligence, (pp. 64–73). Springer. (Best Student Paper).
  4. Huang, D.-W., Gentili, R., & Reggia, J. (2015). A self-organizing map architecture for arm reaching based on limit cycle attractors. In EAI International Conference on Bio-inspired Information and Communications Technologies (BICT), (pp. 7–14). PDF
  5. Huang, D.-W., Katz, G., Langsfeld, J., Gentili, R., & Reggia, J. (2015). A virtual demonstrator environment for robot imitation learning. In IEEE International Conference on Technologies for Practical Robot Applications (TePRA). PDF
  6. Huang, D.-W., Katz, G., Langsfeld, J., Oh, H., Gentili, R., & Reggia, J. (2015). An object-centric paradigm for robot programming by demonstration. In Schmorrow, D. & Fidopiastis, C. (Eds.), Foundations of Augmented Cognition, (pp. 745–756). Springer. PDF
  7. Huang, D.-W., Gentili, R., & Reggia, J. (2014). Limit cycle representation of spatial locations using self-organizing maps. In IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), (pp. 79–84). PDF
  8. Gentili, R., Oh, H., Huang, D.-W., Katz, G., Miller, R., & Reggia, J. (2014). Towards a multi-level neural architecture that unifies self-intended and imitated arm reaching performance. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), (pp. 2537–2540).
  9. Huang, D.-W. & Lin, J. (2010). Scaling populations of a genetic algorithm for job shop scheduling problems using MapReduce. In IEEE International Conference on Cloud Computing Technology and Science (CloudCom), (pp. 780–785). PDF
  10. Huang, D.-W., Lin, P., Gan, C.-H., & Jeng, J.-Y. (2006). A mobility management mechanism using location cache for wireless mesh network. In International Conference on Quality of Service in Heterogeneous Wired/Wireless Networks (QShine).
  11. Cheng, S.-M., Lin, P., Huang, D.-W., & Yang, S.-R. (2006). A Study on distributed/centralized scheduling for wireless mesh network. In International Conference on Wireless Communications and Mobile Computing (IWCMC), (pp. 599–604).

Technical Report

  1. Huang, D.-W., Katz, G., Gentili, R., & Reggia, J. (2016). SMILE: Simulator for Maryland imitation learning environment. Technical report CS-TR-5049, University of Maryland. PDF
  2. Huang, D.-W., Katz, G., Gentili, R., & Reggia, J. (2014). The Maryland virtual demonstrator environment for robot imitation learning. Technical report CS-TR-5039, University of Maryland. PDF