Dear Cambridge AI & Machine Learning Enthusiast,

 

We’re thrilled to announce our next eagerly-anticipated AI & Pizza event, featuring one longer talk from Imperial College London! Mark your calendars for an insightful evening at 5:30 pm on Thursday, July 11th, 2024. It’s your chance to savour the latest advancements in AI and machine learning, right here in Cambridge. Of course, Pizza will be provided after the talk!

 

P.S., We are constantly looking for speakers from related fields. Please do reach out to us (chaoma@microsoft.com; wenbogong@microsoft.com ) if you are interested!

 

Location: The Auditorium, 21 Station Rd

Agenda:

5:30 pm – 6:00 pm: Talks

6:00 pm – 7:00 pm: Networking, Pizza, and Refreshments

 

Speaker: Sonali Parbhoo

Title: Lessons from the Past for Smarter Decisions and Future Wins

Abstract: Reinforcement Learning (RL) has garnered significant attention for its potential to optimize decision-making across various fields by leveraging past data for reasoning about the future. Yet RL faces several key challenges that hinder its broader application. These challenges include the need for vast amounts of data, the complexity of balancing exploration and exploitation, the difficulty of operating in high-dimensional and partially observable environments, and ensuring safety and ethical considerations, especially in sensitive domains like healthcare. Integrating causal knowledge into RL frameworks offers a promising solution to these issues. Causal knowledge can provide a deeper understanding of the underlying mechanisms driving observed outcomes, allowing RL models to make more informed decisions with less data and more robust generalizations. This talk investigates the intersection of RL and causal inference, illustrating how causal models can enhance the efficiency, safety, and interpretability of RL algorithms. By leveraging causal relationships, RL can more effectively navigate complex environments, improving its application in critical areas such as personalized medicine and autonomous systems.  We highlight the potential for causality to transform RL, addressing its fundamental challenges by making better use of historical data, and paving the way for more reliable and intelligent future decisions.

 

Bio: Sonali is an Assistant Professor and leader of the AI for Actionable Impact Group at Imperial College London. Her research focuses on sequential decision-making in uncertainty, causal inference and building interpretable models to improve clinical care and deepen our understanding of human health, with applications in areas such as HIV and critical care. Prior to this, Sonali was a postdoctoral research fellow at Harvard. Her work has been published at a number of machine learning conferences (NeurIPS, AAAI, ICML, AISTATS) and medical journals (Nature Medicine, Nature Communications, AMIA, PLoS One, JAIDS). She was also a Swiss National Science Fellow and was named a Rising Star in AI in 2021. Sonali received her PhD in 2019 from the University of Basel, Switzerland, where she built intelligent

models for understanding the interplay between host and virus in the fight against HIV.  Apart from her research, Sonali is also passionate about encouraging more discussion about the role of ethics in developing safe machine learning technologies to improve society.