Farhad Pourkamali Anaraki
Assistant Professor of Computer Science
Director of Mathematics, Computing, and Data Science Lab
University of Massachusetts Lowell
Email: farhad_pourkamali [at] uml.edu
I am an Assistant Professor of Computer Science at UMass Lowell since Fall 2018. I received my PhD degree in Electrical Engineering from the University of Colorado Boulder in 2017. I was also a Postdoctoral Research Associate in the Applied Mathematics Department at CU Boulder during the subsequent year. Therefore, I have a sound knowledge and understanding of three disciplines - computer science, mathematics/statistics, and electrical engineering. My current research activities encompass two main themes: (1) developing practical and rigorous machine learning algorithms for extracting information from data and (2) using machine learning to assist in decision-making for high-consequence science and engineering problems, including integrated computational materials engineering and structural engineering. The second theme is referred to as Scientific Machine Learning (SciML), i.e., training machine learning algorithms with scientific data to complement traditional domain models.
Scientific Machine Learning (SciML): development and use of artificial intelligence and machine learning in the context of computational decision support for complex systems (e.g., materials science, structural engineering, smart manufacturing)
Scalable machine learning and optimization methods (e.g., scalable clustering and data summarization)
Exploring the interplay between data collection, predictive modeling, and trustworthiness
Generative modeling and neural networks (e.g., variational autoencoders, feature extraction, classification)
Graph partitioning and approximation algorithms (e.g., spectral clustering)
Muti-Scale Models Based on Machine Learning and a Fiber Network Model
Air Force Research Laboratory's Information Directorate (AFRL/RI)
Visiting Faculty Research Program (VFRP)
GOALI: Experimental and Computational Approaches to Tailor Properties of Additively Manufactured Semi-Crystalline Polymers (data science supplement)
Data Science Approaches to Advance High Solids Loading Additive Manufacturing
Visiting Faculty Research Program Recipient, Air Force Research Laboratory Information Directorate (AFRL/RI), 2021
Best Paper Award at 19th International Conference on Machine Learning and Applications (ICMLA), 2020
Early Career Travel Award to attend the SIAM International Conference on Data Mining (SDM), 2018
Gold Research Award in recognition of outstanding contribution to the Department of Electrical, Computer, and Energy Engineering, University of Colorado Boulder, 2017
New journal paper accepted in IEEE Access: "Adaptive Data Compression for Classification Problems." In sharp contrast with prior works, this new approach removes the need to adjust the compression ratio in advance! https://ieeexplore.ieee.org/document/9627182
Workshop paper "Interactive Teaching for Imbalanced Data Summarization" accepted in ICML 2021: https://icml.cc/Conferences/2021/ScheduleMultitrack?event=8351
Parisa's first journal paper got accepted in IEEE Access: Kernel Matrix Approximation on Class-Imbalanced data With an Application to Scientific Simulation, https://ieeexplore.ieee.org/document/9449889
Dr. Pourkamali will serve as the representative of the Computer Science Department on the Kennedy College of Sciences (KCS) Research Council at UMass Lowell.
Dr. Pourkamali is the recipient of the Visiting Faculty Research Program (VFRP), Air Force Research Laboratory's Information Directorate, Summer 2021.
New NASA Grant: "Muti-Scale Models Based on Machine Learning and a Fiber Network Model" with Dr. Scott Stapleton (Award amount: $518k for 3 years)
First accepted paper of 2021 to appear in IEEE Access: Neural Networks and Imbalanced Learning for Data-Driven Scientific Computing with Uncertainties
Best Paper Award at the 19th IEEE International Conference on Machine Learning and Applications (ICMLA): https://www.icmla-conference.org/icmla20/awards.html
New journal paper accepted in IEEE Open Journal of Signal Processing: Scalable Spectral Clustering with Nystrom Approximation: Practical and Theoretical Aspects.
New paper accepted in IEEE International Conference on Machine Learning and Applications (ICMLA): "Kernel Ridge Regression Using Importance Sampling with Application to Seismic Response Prediction." Congratulations to Lydia! The acceptance rate for IEEE ICMLA 2020 is 25%, and our paper is selected for the full ORAL presentation.