About

Rahul Duggal is a highly accomplished PhD student of Computer Science at the Georgia Institute of Technology where he is advised by Prof. Polo Chau. His research focuses on developing neural networks that are efficient to run on resource-constrained platforms, robust to distributional changes in the test data, and resilient to class imbalance in the training data. Rahul's thesis develops algorithms to jointly imbue neural networks with the above properties and draws upon ideas from many research areas such as neural architecture search, filter pruning, early-exiting, adversarial training, and long-tail imbalance. Rahul has over 4 years of relevant experience in the field of research and development. He is currently working as an Applied Scientist II Intern at AWS AI Computer Vision, where he has developed a neural architecture search (NAS) method to search for regression-free models for diverse compute platforms. This project is under review at a top computer vision conference. Previously, he worked as an Applied Scientist II Intern at Amazon, where he developed a heterogeneous visual-search system for fast and efficient image retrieval on the edge. This project got published at CVPR 2021. Rahul's education history includes a Doctor of Philosophy - PhD in Computer Science from the Georgia Institute of Technology, a Bachelor of Engineering (BE) in Computer Engineering from NSIT, and a Bachelor of Engineering, Bachelors in Management Studies from the Department of Management Studies, NSUT. He also completed his schooling from Bluebells School International. Rahul's tech stack includes Research Scientist, AWS, AI, Search, Computer Vision, Neural Networks, Deep Learning, test, and ML. He is passionate about discussing the latest advances in ML, CV, and deep learning, and is open to connecting with like-minded individuals.