Research
I am currently working under the supervision of Prof. Gyorgy Turan.
My research explores explainability in Artificial Intelligence. We are investigating the mathematical underpinnings and the philosophical foundations for scientific explanations in black-box AI algorithms. I work with graph/network data. I spend most of my time building Graph Neural Network models and analyzing studying their behavior. Social networks, molecules as a network of atoms and their bonds, knowledge bases, the relationship between financial instruments, transportation networks, etc., are some examples of graph data.
I also spend time thinking about the Philosophy of science, ethics & fairness in AI, robust ML algorithms, causality, knowledge representations & reasoning, and statistical learning theory.
Previously, I worked as a researcher in Human-Centered Computing. We designed mechanisms for understanding contexts of co-located groups in small meeting spaces. The work aimed at inferring contextual information based on the geometric configuration and physical orientation of participants.
Projects
STK - Scientific Toolkit
Implementation of low level datastructures and algorithms for Machine Learning, in C++17/C++20
iConn - Interpretable Convolutional Neural Network
A demo implementation of explainable covolutional neural networks using 2D images using Mutual Information.
proxe - Proxemics Engine Suite
A library and UI tool suite written in Qt/C++ for conducting studies of co-located groups.
That UI application also has an analysis suite for coding and analysing observations.
Publications
H. Naik, Gyorgy Turan, Explanation from Specification - Explainable Agency in Artificial Intelligence Workshop at the 35th AAAI Conference on Artificial Intelligence - A Virtual Conference, February 2-9, 2021
H. Naik, D. Chattopadhyay, IPME Workbench: A Data Processing Tool for Mixed-Methodology Studies of Group Interactions - CHI EA ‘19 Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems. Paper No. LBW1517. Glasgow, Scotland, UK – May 04-09, 2019
K. Yoshii, H. Naik, C. Yu, P. Beckman, Extending and benchmarking the “Big Memory” implementation on Blue Gene/P Linux - International Workshop on Runtime and Operating Systems for Supercomputers (ROSS 2011), Tuscon, AZ
R. Gupta, H. Naik and P. Beckman, Understanding Checkpointing Overheads on Massive-Scale Systems: Analysis on the IBM Blue Gene/P System – International Journal of High Performance Computing Applications (IJHPCA), May 2010
K. Yoshii, K. Iskra, H. Naik, P. Beckman and P. C. Broekema, Performance and Scalability Evaluation of “Big Memory” on Blue Gene Linux – International Journal of High Performance Computing Applications (IJHPCA), May 2010
P. Balaji, H. Naik and N. Desai, Understanding Network Saturation Behavior on Large-Scale Blue Gene/P Systems – The 15th International Conference on Parallel and Distributed Systems (ICPADS’09), Shenzhen, China
H. Naik, R. Gupta and P. Beckman, Analyzing Checkpointing Trends for Applications on Petascale Systems – Second International Workshop on Parallel Programming Models and Systems Software (P2S2) for High-End Computing in conjunction with International Conference on Parallel Processing (ICPP), 2009
K. Yoshii, K. Iskra, P. C. Broekema, H. Naik, and P. Beckman, Characterizing the Performance of Big Memory on Blue Gene Linux – In “Proceedings of the 2nd Int. Workshop on Parallel Programming Models and Systems Software for High-End Computing,” Vienna, Austria, Sept. 2009.