Gal Benor

Unveiling the Why: Harnessing XAI to Unlock Hidden Data Insights
Gal-Benor

Abstract

In today’s rapidly evolving landscape, especially in areas like fraud detection and healthcare, relying on opaque machine learning models is no longer an option. Join us for this roundtable as we delve into the power of eXplainable AI (XAI) to shed light on these “black-box” models. Together, we’ll explore how XAI can provide transparency, uncover hidden insights, and enhance decision-making processes across a wide range of fields, from fraud prevention to medical diagnostics and beyond.

Bio

Gal Benor is a machine learning scientist at PayPal. In her day-to-day projects she focuses on developing transparent fraud detection models that safeguard users. She is passionate about eXplainable AI (XAI) and works to make machine learning more interpretable and tailored to specific needs. Gal earned a BSc in computer science from Ben-Gurion University and an MSc in applied mathematics and systems biology from the Weizmann Institute of Science where she focused her research on breast cancer – an area where transparency is critical and black-box models are not an option.

Agenda

8:45 Reception
9:30 Opening remarks by WiDS TLV ambassadors
9:45 Dr. Mor Geva , Tel Aviv University: “MRI for Large Language Models: Mechanistic Interpretability from Neurons to Attention Heads”
10:15 Panel: “Pioneering Progress: a strategic look at the GenAI revolution and the new role of data scientists“
Shani Gershtein, Melingo
Mirit Elyada Bar, Intuit
Dr. Asi Messica, Lightricks
Moderated by Nitzan Gado, Intuit
10:45 Poster pitches
10:55 Break
11:10 Lightning talks session
12:30 Lunch & poster session
13:30 Roundtable session & poster session
14:30 Roundtable closing
14:40 Shunit Agmon, Technion: “Bridging the Gender Gap in Clinical AI: Temporal Adaptation with TeDi-BERT”
15:00 Shaked Naor Hoffmann, Apartment List: “Building Generative AI Agents for Production: Turning Ideas into Real-World Applications”
15:20 Closing remarks
15:30 The end