Detecting and Correcting Unfairness in Machine Learning | AISC

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=nbsd-L9V5L0


Duration: 1:32:22
117 views
1

Speaker(s): Matthew Brems
Facilitator(s): Serena McDonnell

Find the recording, slides, and more info at https://ai.science/e/detecting-and-correcting-unfairness-in-machine-learning--WpR6TFE32r8qHtqEGWMt

Motivation / Abstract
You've heard stories about a husband getting a much higher credit limit than his wife, a medical diagnostic test working better for some people than others, or certain people being approved for loans at a higher rate than others.

Unfairness can creep into our data in a variety of ways, and a machine learning model can often make the problem worse, not better!

We'll start by discussing a high-level understanding of fairness in machine learning. Then we'll cover methods for detecting whether or not unfairness is present and methods for correcting for unfairness, and open up the floor for discussion.

Fairness in machine learning is a critical topic to understand. Given the impact that data has on people's lives, those of us using data to make decisions need to be aware of fairness!

What was discussed?
Our talk will cover three things:

1. There are many ways to define unfairness, so we'll agree on a definition and describe what it means.

2. We'll learn techniques for detecting whether or not unfairness is present in our application.

3. If unfairness is present, how do we fix it? We'll learn techniques for correcting for unfairness.

We will focus on applications in finance: think loans, income, credit scores. However, these techniques can be applied well beyond the realm of finance, so no background in finance is required! We'd love for you to bring your own applications for us to discuss.


------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit https://ai.science for more details



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2020-11-11[GATA] Learning Dynamic Belief Graphs to Generalize on Text-Based Games | AISC
2020-11-11DrWhy.AI - Tools for Explainable Artificial Intelligence | AISC
2020-11-06Similarity Search for Efficient Active Learning and Search of Rare Concepts | AISC
2020-11-06Identifying Influential Individuals in Complex Networks: An Overview | AISC
2020-11-05Da Xu (Walmart Labs): Inductive Representation Learning on Temporal Graphs | AISC
2020-11-04AI, Democracy, & Disinformation
2020-10-29Application of Bayesian neural networks for aircraft safety | AISC
2020-10-28AI and ML toward Telcom future | AISC
2020-10-27Investing in Emerging Technology & The Nuts & Bolts of How to Raise Money for your Startup | AISC
2020-10-23The People, Politics, & Histories Behind Machine Learning Datasets | AISC
2020-10-23Detecting and Correcting Unfairness in Machine Learning | AISC
2020-10-23Highly Recommended: A Fireside Chat with AISC's Resident Experts on Recommender Systems
2020-10-23A Fireside Chat with AISC NLP experts
2020-10-22Machine Learning in Environmental Science and Prediction: An Overview | AISC
2020-10-22Battery Modelling using Data-Driven Machine Learning | AISC
2020-10-21BERTology Meets Biology: Interpreting Attention in Protein Language Models | AISC
2020-10-20Design for Augmentation (not Automation) | AISC
2020-10-16Genomics with Deep Learning: A Concise Overview | AISC
2020-10-15Designing quantum computers with generative models | AISC
2020-10-15Explainable AI for Time Series - Literature Review | AISC
2020-10-15Towards a Critical Race Methodology in Algorithmic Fairness | AISC


Tags:
deep learning
machine learning