Joseph Paul Cohen PhD

Applied Scientist at Amazon AWS Health AI
Associate Fellow at AIMI, Stanford University
Director at The Institute for Reproducible Research

Former Deep Learning for Ultrasound at Butterfly Network
Former Postdoctoral Research Fellow at AIMI, Stanford University
Former Postdoctoral Fellow at Mila, Quebec AI Institute,University of Montreal

My goal is to democratize access to healthcare to provide the highest quality healthcare to everyone (specifically those not served by the current system; 8% in the US and 25% globally). Automation and AI can increase the supply of providers to fill this need. I am working to identify and overcome issues limiting the deployment of AI tools in healthcare. My core research directions are representation learning, generalization, and model interpretability.

Bio: Joseph Paul Cohen is a researcher and engineer currently focusing on the challenges in deploying AI tools in medicine. Specifically focusing on computer vision, explainability, and representation learning. Joseph is currently an Applied Scientist at Amazon working on Health AI. Prior to that he worked at Butterfly Networks, a portable ultrasound manufacturer, developing new AI tools. Prior to that, Joseph was a postdoc at Stanford University in the Center for Artificial Intelligence in Medicine & Imaging working on tools for chest X-ray analysis with AI. And prior to that a postdoc at Mila, the Quebec AI Institute, where he led the medical deep learning research group. Joseph pioneered the use of on-device deep learning for blind assistance tools with the creation of BlindTool – a mobile vision aid Android app. Joseph is the founder and director of a non-profit organization which operates ShortScience.org and Academic Torrents. He has organized events such as the Innovation, Hacking, Free and Open Source and Mars and Beyond events at the Museum of Science Boston and the Artificial Intelligence for Genomics boot camp at Concordia University and the IVADO Data Science and Healthcare school.

, LinkedIn, Google Scholar, ShortScience.org

Selected Projects