Explaining and Understanding Machine Learning
Details
Our main topic of discussion this month is explainability in Machine Learning. Soysal Degirmenci will presenting and sharing his recent work.
Agenda
Introduction and announcements (10:30 AM - 10:45 AM)
Main Talk (10:45 AM - 11:30 AM)
Discussion and Networking (11:30 AM -12:00 PM)
Description:
We're in an era of Machine Learning (ML) resurgence. There's been a lot of excitement around AI and ML, backed by some state-of-the-art results in many domain like computer vision and natural language processing. Not only these successful results have been shown in academia, a lot of companies have been putting these complex models into production, to be used in everyday life. In this era, the main focus seems to be the performance for these models. While it's remarkable that now we know how to train very accurate and very complex models, it's important to spend more time to understand how these complex models work, why they make certain decisions for the sake of transparency and trust. In this talk, we'll go over different techniques on how to explain and understand machine learning models, and demonstrate these techniques on some applications.
Directions and Parking:
http://www.sdsc.edu/about_sdsc/visitor_info.html