ECE SEMINAR ALVARO VELASQUEZ

Abstract
Neuro-symbolic AI presents tremendous opportunities for more efficient foundation models in the form of integrating classical symbolic methods with deep learning. However, that integration is faced with several key challenges, including the correspondence between symbolic and neural systems and the scale of modern AI models. In this talk, we cover some of these challenges and discuss potential pathways forward, including the role that neuro-symbolic AI can play in the development of more generalizable autonomous systems.
Bio

Alvaro Velasquez is a program manager at DARPA, where he currently leads programs on neuro-symbolic AI and autonomy. Before that, Alvaro oversaw the machine intelligence portfolio for the Information Directorate of the Air Force Research Laboratory (AFRL). Alvaro is a recipient of the distinguished paper award from AAAI and best paper and patent awards from AFRL. He has authored over 100 papers and three patents, serves as Associate Editor of the IEEE Transactions on Artificial Intelligence, and is a co-founder of the Neuro-symbolic Systems (NeuS) conference.