Description
【The 7th Seminar】
Date and Time: March 17th 10:00am – 11:00am(JST)
Venue: Zoom webinar
Language: English
Speaker: Dimitris Tsipras (Standford University)
Title: Controlling model behavior beyond the training data
Abstract:The canonical recipe for building a machine learning system involves training a model on a dataset that is designed to capture a specific task. However, creating a good dataset is not always easy. In this talk, I will describe how different design choices can cause our dataset to systematically deviate from the real-world task it is intended to capture. I will then present a new paradigm for interacting with models after training by rewriting their predictions rules. This paradigm allows a model designer to directly modify the behavior of the model to adapt it to new environments or fix bugs in its behavior.
