Next Meetup

Algorithmic Fairness: Predict Responsibly
Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer We will look at the importance of defining fairness in a rigorous way for the agents involved in decision making based on Machine Learning. Agenda: Please arrive on time. Doors close at 6:20pm. - 6:00pm Networking - 6:20pm Announcements - 6:30pm Talk - 7:45pm Networking This talk is based on the following paper, and presented by one of the authors of the paper: Abstract: In many machine learning applications, there are multiple decision-makers involved, both automated and human. The interaction between these agents often goes unaddressed in algorithmic development. In this work, we explore a simple version of this interaction with a two-stage framework containing an automated model and an external decision-maker. We propose a learning algorithm (learning to defer) which accounts for potential biases held by external decision-makers in a system. Experiments demonstrate that learning to defer can make systems not only more accurate but also less biased. Even when working with inconsistent or biased users, we show that deferring models still greatly improve the accuracy and/or fairness of the entire system. Speaker: David Madras is a PhD student and researcher in the Machine Learning Group at the University of Toronto and the Vector Institute, supervised by Richard Zemel. His research focuses on fairness and ethics in machine learning and algorithmic decision-making systems, and on developing tools such as deep learning and causal inference for usage in those systems. Hope to see you there! This is a joint event with Toronto Deep Learning Series. You can find the full list of the series here:

Sidewalk Labs

307 Lake Shore Blvd E · Toronto, on

    Past Meetups (32)

    What we're about

    Deep Learning TO is a space for those interested in having scientific discussions related to Deep Learning.

    - You will meet other people interested in Deep Learning
    - You will connect to people working in Machine Learning
    - You will work with data
    - You will learn by doing

    We are having have 2 meetings per month:

    - the first Thursday of every month from 8am to 10 am.
    - the third Thursday of every month from 8am to 10 am.

    We will start by going through the following tutorials in order:

    And then we will choose topics by consensus.

    - Machine Learning knowledge
    - Programming knowledge
    - Math

    Members (2,941)

    Photos (54)

    Find us also at