Vinu Joseph

VINU JOSEPH

Hometown: Bangalore, India

Student Page: https://www.vinujoseph.org/

Research:  Vinu’s current research focuses on optimizing deep neural networks for performance and scalability. More broadly, His research is at the intersection of systems, programming languages and machine learning, to create a more efficient, performant, secure, privacy-preserving and correct software. His PhD research has been mainly focused on deep neural network compression for resource efficient inference and robustness. He is also interested interested in applying machine learning to challenging problems within programming systems. In collaboration with NVIDIA research he developed Condensa: A Programming system for Model Compression (https://nvlabs.github.io/condensa/).

Bio: Vinu is a PhD candidate in Computer Science at the School of Computing at the University of Utah, Salt Lake City, working on efficient deep learning computing, robustness and security of deep learning algorithms, advised by Prof. Ganesh Gopalakrishnan. Prior to graduate studies, Vinu worked at ARM Inc. During his tenure at ARM, he was a recipient of the Bravo award for developing the programmer’s model for verifying real-time (‘R’) profile architecture which provides high-performing processors for safety-critical environments. Vinu applies his research in AI for social good, via Project Cinchona, (currently, with the goal of improving malaria parasite detection from red blood cells using deep learning in resource constrained regions). He received his bachelor’s degree at the Department of Electronics and Communication Engineering from CMR Institute of Technology, Bangalore, affiliated to the Visvesvaraya Technological University and his Undergraduate research was on efficient double-precision floating point arithmetic on FPGAs at National Aerospace Laboratory, India.