Here is my resume.

Research Interests:

  • Adversarial machine learning for neural networks
  • Model robustness for deep learning and model-based methods
  • High-dimensional data analysis on regression and clustering


See this page for more details.

  • Adversarial Learning and Interpretability for Neural Networks (Sep. 2017 - Present)
    • Collaborated and published top AI/ML papers (NIPS & AAAI) with IBM Research
    • Developed query-ecient generation of adversarial examples from black-box ML models using unsupervised learning techniques, with at least 93% query reduction <github>
    • Improved interpretability of neural networks using adversarial examples <github>
  • Robust High-dimensional Non-linear Data Analysis (Sep. 2015 - Present)
    • Estimated nonlinear partially-latent high-to-low association through inverse regression and parsimonious mixture model
    • Achieved computing efficiency for EM algorithm with analytical solutions
    • Conducted robust high-dimensional data cluster analysis with cluster size constraints
    • See here for visualization of the face dataset
  • Spatial Association among Brain Regions for Identifying ASD (Sep. - Dec. 2016)
    • Built predictive model for identifying Autism Spectrum Disorder using fMRI data
    • Selected prognostic brain regions using spatial correlated prior distribution with OpenBUGS
  • Information Propagation Control in Network of Networks (Sep. - Dec. 2015)
    • Identified influential links for event propagation in massive Twitter networks — 15% more effective than state-of-the-art
    • Visualized information propagation using Python package NetworkX
    • Used real twitter data as for evaluation
  • Automated Feature Selection for Code Optimization Options (Sep. - Dec. 2015)
    • Selected only 18% of key program features for determining program optimization tuning parameters while maintaining comparable program optimization performance
  • C++ Implementation for Generalized Linear Models (Sep. - Dec. 2015)
    • Accelerated general linear models with lasso and elastic-net regularization using C++.
    • Achieved comparable efficiency with the original Fortran acceleration
  • U-phi: Wireless Body Area Network Core Technology (Sep. 2009 – Jul. 2012)
    • Developed energy efficient Medium Access Control protocol on embedded system
    • Controlled quality of service in heterogeneous Wireless Body Area Network


[1] Tu, C. C., Ting, P. S., Chen, P. Y., Liu S., Zhang, H., Yi, J., Hsieh, C. J., Cheng, S. M. (2018). “AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks,” To appear in Proceedings of AAAI Conference on Artificial Intelligence (AAAI) <arXiv>

[2] Dhurandhar, A., Chen, P. Y., Luss, R., Tu, C. C., Ting, P. S., Shanmugam, K., Das, P. (2018). “Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives,” To appear in Proceedings of Advances in Neural Information Processing Systems (NIPS) <arXiv> <Forbes converage>

[3] Chen, P. Y., Tu, C. C., Ting, P. S., Lo, Y. Y., Koutra, D., Hero III, A. O. (2018). “Identifying Influential Links for Event Propagation on Twitter: A Network of Networks Approach,” IEEE Transactions on Signal and Information Processing over Networks. <arXiv>

[4] Ting, P. S., Tu, C. C., Chen, P. Y., Lo, Y. Y., Cheng, S. M. (2017). “FEAST: An Automated Feature Selection Framework for Compilation Tasks,” 31-st IEEE International Conference on Advanced Information Networking and Applications (AINA). <arXiv>

[5] Tu, C. C., Forbes, F., Lemasson, B., Wang, N., “Structured Mixture of Gaussian Locally Linear Mapping for High-to-Low Dimension Prediction”. (under review)

[6] Cheng, S., Huang, C., Tu, C. C. (2011). “RACOON: A multiuser QoS design for mobile wireless body area networks,” Journal of medical systems, 35(5), 1277-1287. <paper>

Work Experience:

  • Audio Machine Learning Intern, Bose Corporation, USA (Jun. 2018 - Aug 2018)
    • Developed data processing pipeline and system prototype using Tensorflow and AWS
    • Conducted research on Audio Source Separation application with deep learning methods
    • Implemented web interface for demonstration using JavaScript and Django
    • Related skills: Deep learning, Tensorflow, JavaScript, Django, AWS
  • Graduate Student Research Assistant, University of Michigan, USA (Sep. 2014 - Present)
    • Improved model robustness against adversarial examples and outliers
    • Devised an algorithm to solve non-linear high-dimensional regression problems via inverse regression and local linearity
    • Related skills: Expectation-Maximization algorithm, Mixture of regression model, high performance computing, parallel computing
  • Research Assistant, Institute of Electronics Engineering, National Chiao Tung University, Taiwan (Jul. 2013 - Jul. 2014)
    • Designed a prototype for low-power high-speed distributed machine learning platform under Hadoop framework combined with embedded system and ASIC hardware design
    • Consumed 40% of power with comparable computing time using large-scale data for common machine learning algorithms
    • Related skills: Embedded system, Hadoop, Java
  • Software Engineer Intern, MediaTeK Inc., Taiwan, (Jul. 2011 – Sep. 2011)
    • Developed graphical tools for phone packet analysis using C#
    • Implemented event oscilloscope for task tracking and root cause analysis
    • Related skills: C#, object-oriented programming, graphic user interface

Teaching Experience:

  • Graduate Student Instructor, University of Michigan, USA
    • Computational Methods and Tools in Statistics (STATS 506), Fall 2017, Fall 2018
    • Statistical Learning I: Regression (STATS 500), Winter 2017
    • Introduction to Theoretical Statistics (STATS 426), Winter 2016
    • Introduction to Statistics and Data Analysis (STATS 250), Fall 2015
    • Introduction to Probability & Statistics (STATS 412), Fall 2014
  • Teaching Assistant, Department of Electronics Engineering, National Chiao Tung University, Taiwan
    • Microelectronics and Circuit Design Laboratory (English medium class), Fall 2010 to Spring 2012

Awards and Honors:

  • NIPS Travel Award, NIPS Foundation, Dec. 2018
  • Rackham Travel Grant, University of Michigan, Jul. 2018
  • Rackham Summer Award, University of Michigan, May 2016
  • Departmental Support Fellowship, Sep. 2014
  • The Zhu Shun Yi He Qin Scholarship, ZyXEL Communications Corporation May 2011
  • Outstanding Student Entrance Scholarship, Department of Electronics Engineering, National Chiao Tung University, Sep. 2010
  • Outstanding Student Contribution Scholarship, National Chiao Tung University, Jun. 2010