Evolution of Foundational Models: From Deep Learning in Healthcare to Neuro-inspired AI

Wednesday, April 24, 2024

Foundational models have rapidly evolved from deep learning networks to generative AI. In this talk, I will give an overview of the various projects relating to foundational models in my research lab covering work in building generalized frameworks of multimodal fusion for many downstream tasks in healthcare and beyond, to the latest neuro-inspired models for storage and retrieval of information in computer vision. I will also cover some newer topics such as image-driven fact-checking of textual reports from generative AI in an effort to build responsible foundational models.

 

Post Talk Link:  Click Here

Passcode: eq2!8JcM

 

Speaker/s

Dr. Tanveer Syeda-Mahmood is an IBM Fellow and a Global Imaging AI leader in IBM Research. As a worldwide expert in imaging, she is leading the company's future in Multimodal Bioinspired AI and defining new features in WatsonX series of products. Until recently, she was the Chief Scientist of the Medical Sieve Radiology Grand Challenge that helped launch the field of Radiology AI and the IBM Watson Health Imaging business. As an IBM Fellow, she is also involved in long-term strategic thinking on the evolution of the field of AI. Dr. Tanveer Syeda-Mahmood graduated with a Ph.D from the MIT Artificial Intelligence Lab in 1993. Prior to coming to IBM, she led the image indexing program at Xerox Research and was one of the early originators of the field of content-based image and video retrieval. Over the past 30 years, her research interests have been in a variety of areas relating to artificial intelligence ranging from computer vision, image and video databases, to applications in medical image analysis, healthcare informatics and clinical decision support. Dr. Syeda-Mahmood has chaired many international conferences over the years including IEEE CVPR (2008), IEEE HISB (2011), IEEE ISBI (2021), MICCAI (2023). She is a Fellow of IEEE, MICCAI, AIMBE (American Institute for Medical and Biological Engineering) and AAIA (Asian Association of Artificial Intelligence).

Related