When: September 14 at 12:00 EST
Title: Symbolic AI in a Machine Learning World
Speaker: Prof. Alon Halevy, the Director at Facebook AI
The key technical problems that online social networks focus on today are detecting policy violating content (e.g., hate speech, misinformation) and ranking content to satisfy their users’ needs. By nature, these problems are somewhat vague and need to handle multi-modal content in many languages, and therefore do not naturally lend themselves to AI techniques based on declarative representations and reasoning. However, the machine learning techniques that are employed also have some drawbacks, such as the fact that it is hard to update their knowledge efficiently or to explain their results. In this talk I will outline a few opportunities where methods from symbolic AI, combined appropriately into the machine learning paradigm, can ultimately have an impact on our goals. As one example, I will describe Neural Databases, a new kind of database system that leverages the strength of NLP transformers to answer database queries over text, thereby freeing us from designing and relying on a database schema.
When: September 13 at 12:00 EST
Title: Interpretable Machine Learning with Rule-Based Modeling
Speaker: Prof. Ryan Urbanowicz, University of Pennsylvania
Rules-based machine learning with algorithms such as ‘Learning Classifier Systems’ (LCS) offer attractive alternatives to popular ML modeling techniques. They not only model complex relationships but can do so in an inherently interpretable manner. This makes their application particularly relevant in fields such as medicine, where achieving high predictive performance must be paired with model transparency to foster trust, promote knowledge discovery, identify/avoid sources of bias, and maintain accountability. This talk will discuss the unique aspects of LCS as a supervised learning methodology, and examine avenues and opportunities for interpretable ML modeling in rule-based frameworks.