News

With advances in deep learning, machines are now able to “predict” a variety of aspects about life, including the way people interact on online platforms or the way they behave in physical environments. This is especially true in computer vision applications where there is a growing body of work on predicting the future behavior of moving objects such as vehicles and pedestrians. 

“However, while machine-learning methods are now able to match — and sometimes even beat — human experts in mainstream vision applications, there are still some gaps in the ability of machine-learning methods to predict the motion of ‘shape-shifting’ objects that are constantly adapting their appearance in relation to their environment,” said Anuj Karpatne, assistant professor of computer science and faculty at the Sanghani Center for Artificial Intelligence and Data Analytics. Click here to read how Karpatne and his team will tackle this challenge in their National Science Foundation-sponsored research.

Conferences have been a big part of Arka Daw’s life as a Ph.D. student this past academic year.

Daw presented “Physics-Guided Architecture (PGA) of Neural Networks for Quantifying Uncertainty in Lake Temperature Modeling” in proceedings at the 2020 SIAM International Conference on Data Mining (SDM), and “PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics” in proceedings at the 2021 ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).

In addition, he participated in the NeurIPS ML4PS Workshop, “Physics-Informed Discriminator (PID) for Conditional Generative Adversarial Nets.”

Daw’s broader research interests include artificial intelligence and deep learning but, more specifically, his work is geared towards formulating generic ways of coupling scientific knowledge with conventional deep learning approaches. 

The research he presented at the SIAM conference involved predicting the temperature of lakes at different depths. 

“Our proposed solution included a specialized design of a seq-to-seq model where a specific physics-driven inductive bias was infused directly into the model architecture,” said Daw, who is advised by Anuj Karpatne, “It demonstrated that combining scientific knowledge with deep learning models can not only improve their generalizability but also provide meaningful uncertainty estimates.”

During his undergraduate studies in electronics and telecommunication engineering at Jadavpur University, India, Daw had the opportunity to work on retinal artery-vein classification during a research internship at the Pattern Recognition and Image Analysis group at University of Muenster, Germany. 

“This is when I realized the immense potential of deep learning in solving real-world problems and decided to pursue higher studies in the broader field of artificial intelligence,” he said. 

Daw said he was drawn to Virginia Tech due to its eminence in world-class research and exemplary work of faculty in the Department of Computer Science and at the Sanghani Center.

“I am exceedingly fascinated by Dr. Karpatne’s approach to solving real-world scientific problems and how he works towards shaping the emerging field of science-guided machine learning,” he said. “I am very fortunate to have him as my advisor.”

Daw said that being a student at the Sanghani Center has provided him the opportunity to work with students and faculty of diverse backgrounds and research focus.  

“Everyone is always very supportive, really fun to work with, and provides great advice when you need it,” he said.

Daw is projected to graduate in Spring 2023.

With restrictions to working in physical office space still in effect, graduate students at the Sanghani Center are working remotely this summer for companies, labs, and programs from coast to coast. Students are not only gaining real-world experience from internships and other opportunities but, in many cases, they are also able to advance their own research interests.

Following is a list of Sanghani Center students and the work they are doing:

Badour AlBahar, a Ph.D. student in electrical and computer engineering, is a computer vision intern at Adobe Vision group in San Jose, California. She is working on human reposing and animation. Her advisor is Jia-Bin Huang.

Sikiru Adewale, a Ph.D. student in computer science, is a software development engineer intern at Amazon Web Service in Seattle, Washington. He is working on data transfer and storage on the AWS snowball device. His advisor is Ismini Lourentzou.

Vasanth Reddy Baddam, a Ph.D. student in computer science, is an research intern at Siemens in Princeton, New Jersey. He is working on contributing to industrial research projects on leveraging machine learning to analyze multi-agent reinforcement learning (MARL) algorithms and implement them. His advisor is Hoda Eldardiry. 

Subhodip Biswas, a Ph.D. student in computer science, is working on Bayesian optimization techniques for automated machine learning (AutoML) and robust artificial intelligence systems as part of the Journeyman Fellowship he received from the DEVCOM Army Research Laboratory (ARL) Research Associateship Program (RAP) administered by the Oak Ridge Associated Universities (ORAU). His advisor is Naren Ramakrishnan.

Jie Bu, a Ph.D. student in computer science, is a research intern at Carbon 3D in Redwood City, California. He is working on artificial intelligence-powered computational geometry. His advisor is Anuj Karpatne.

Si Chen, a Ph.D. student in computer engineering, is a research intern at InnoPeak Technology in Seattle, Washington. She is working on research on model privacy protection. Her advisor is Ruoxi Jia.

Kai-Hsiang Cheng, a master’s degree student in computer science, is an intern at GTV Media Group in New York City. He is working on the content management system of the media’s platform. His advisor is Chang-Tien Lu.

Riya Dani, a master’s degree student in computer science, is a software engineer intern at Microsoft. She is working on web application developments under Azure. Her advisor is Ismini Lourentzou.

Debanjan Datta, a Ph.D. student in computer science, is an intern on the Amazon Web Services team at Amazon in Seattle, Washington. He is working on time series characterization and classification.  His advisor is Naren Ramakrishnan.

Arka Daw, a Ph.D. student in computer science, is an applied scientist intern at Amazon Web Services Lambda Science Team in Seattle, Washington.  He is working on developing an automated causal machine learning framework for setting up experiments and estimating causal effects from observational data. His advisor is Anuj Karpatne.

Yue Feng, a Ph.D. student in electrical and computer engineering, is an intern with the Snap Research Creative Vision Team in Santa Monica, California. She is working on a 3D computer vision project. Her advisor is Jia-Bin Huang.

Chen Gao, a Ph.D. student in electrical and computer engineering, is a research intern at Google in Cambridge, Massachusetts. He is working on creating video panoramas using a cellphone. His advisor is Jia-Bin Huang.

Jianfeng He, a Ph.D. student in computer science, is an intern at Tencent AI Lab in Seattle,Washington. He is working on research about multi-modal dialogue with mentors Linfeng Song and Kun Xu. His advisor is Chang Tien-Lu.

Taoran Ji, a Ph.D. student in computer science, is an intern at Moody’s Analytics in New York City. He is working on analyzing credit and financial data for the global financial markets, which will drive algorithmic improvements in Moody’s Analytics core machine learning and artificial intelligence-driven products. His advisor is Chang-Tien Lu.

Adheesh Juvekar, a Ph.D. student in computer science, is a machine learning and natural language processing intern at Deloitte & Touche LLP. He is working on automatically extracting relevant information from transactional invoices using state of the art deep learning techniques. His advisor is Edward Fox.

M. Maruf, a Ph.D. student in computer science, is a machine learning engineering intern at Qualcomm GNSS/location team in Santa Clara, California. He is applying machine learning techniques to hybrid technology fusion for navigation/positioning in mobile, wearable, automotive, and micro-mobility applications. His advisor is Anuj Karpatne.

Nikhil Muralidhar, a Ph.D. student in computer science, received an Applied Machine Learning Summer Research Fellowship at Los Alamos National Lab in Los Alamos, New Mexico, to work with researchers on physics-informed machine learning for modeling adsorption equilibria in fluid mixtures. His advisor is Naren Ramakrishnan. 

Makanjuola Ogunleye, a Ph.D. student in computer science, is an application support engineer intern at Northwestern Mutual in Milwaukee, Wisconsin. His duties include coding, testing, and implementing complex programs from user specifications. He is also performing client data analysis to support engineering technology to improve and facilitate customer success. His advisor is Ismini Lourentzou.

Nishan Pokharel, a master’s degree student in computer science, is a software engineering intern at Capital One in Mclean, Virginia.  He is working on network infrastructure automation. His advisor is Chris North

Avi Seth, a master’s degree student in computer science, is serving as a graduate team leader this summer for Virginia Tech’s Data Science for the Public Good program. The group works on projects that address state, federal, and local government challenges around today’s relevant and critical social issues. His advisor is Ismini Lourentzou.

Mia Taylor, a master’s degree student in computer science, is a software development intern at Amazon Web Services in Seattle, Washington. Her team is working with Comprehend AutoML which allows customers to build customized natural language processing models using their own data. Her advisor is Lifu Huang.

Yiran Xu, a Ph.D. student in electrical and computer engineering, is an intern with the Snap Research Creative Vision Team in Santa Monica, California. He is working on 3D human reconstruction and video generation/manipulation. His advisor is Jia-Bin Huang.

Shuaicheng Zhang, a Ph.D. student in computer science, is a natural language processing (NLP) research intern at Deloitte in New York City. He is part of the Audit and Assurance AI innovation team, working on open information extraction on internal control files to help auditors effortlessly process these files. His advisor is Lifu Huang.

Yuliang Zou, a Ph.D. student in electrical and computer engineering, is a research intern at Waymo in Mountainview, California. He is working on the perception problem for self-driving cars.  His advisor is Jia-Bin Huang.