Fairness Criteria, Exploring Fairness in Machine Learning

preview_player
Показать описание
MIT RES.EC-001 Exploring Fairness in Machine Learning, Spring 2020
Instructor: Mike Teodorescu

This video presents the confusion matrix, including true negatives, true positives, false negatives, and false positives. It discusses how to choose between different fairness criteria such as demographic parity, equalized odds, and equalized opportunity.

License: Creative Commons BY-NC-SA

  1. MIT OpenCourseWare
  2. confusion matrix
  3. demographic parity
  4. equalized opportunity
  5. equalized odds
  6. fairness
Рекомендации по теме
Fairness Criteria, Exploring 0:07:07

Fairness Criteria, Exploring Fairness in Machine Learning

Protected Attributes and 0:06:18

Protected Attributes and 'Fairness through Unawareness,' Exploring Fairness in Machine Lea...

Solar Lighting Example, 0:06:20

Solar Lighting Example, Exploring Fairness in Machine Learning

Exploring Fairness in 0:05:15

Exploring Fairness in Machine Learning: Background

Definitions of Fairness 0:10:32

Definitions of Fairness in Machine Learning | Equal Opportunity, Equalized Odds & Disparate Impa...

Exploring fairness in 0:30:07

Exploring fairness in AI for the Labor Market | Fairness and Bias in AI | Eduard Fosch-Villaronga

Michael Kearns: “Fairness” 0:02:57

Michael Kearns: “Fairness” in Machine Learning

Exploring fairness in 0:36:26

Exploring fairness in the transductive setting for neuroimaging studies - FAIMI 2022

Fairness in Medical 0:40:48

Fairness in Medical Algorithms: Threats and Opportunities

Fairness in Machine 0:05:52

Fairness in Machine Learning : Metrics based on Confusion Matrix

ID 61: How 0:03:00

ID 61: How fair is your graph? Exploring fairness concerns in neuroimaging studies

Tutorial -- Causal 2:03:34

Tutorial -- Causal Fairness Analysis [ICML 2022]

Fairness in Risk 0:19:09

Fairness in Risk Assessment Instruments: Post-Processing to Achieve Counterfactual Equalized Odds

Survey: Fairness Criteria 0:07:14

Survey: Fairness Criteria Introduced

Fairness Indicators for 0:06:17

Fairness Indicators for TensorFlow (TF Dev Summit '20)

A marketer’s guide 0:00:31

A marketer’s guide to machine learning fairness

Privacy vs Fairness 0:42:01

Privacy vs Fairness in Computer Vision with Alice Xiang - 637

USAID Appropriate Use 0:09:01

USAID Appropriate Use Framework, Exploring Fairness in Machine Learning

Responsible AI (17/30) 0:14:08

Responsible AI (17/30) - Introduction to Fairness Criteria

Introduction to Algorithm 0:05:46

Introduction to Algorithm Fairness | Causes, Measuring & Preventing Unfairness in Machine Learni...

Measuring Fairness in 0:10:51

Measuring Fairness in Machine Learning Systems

What Really Matters 0:41:56

What Really Matters for Fairness in Machine Learning: Delayed Impact and Other Desiderata

Fred Morstatter: Exploring 0:15:23

Fred Morstatter: Exploring Fairness and Bias in Machine Learning

Fairness in Machine 1:20:55

Fairness in Machine Learning

Комментарии
Автор

Thanks for the video! One question: How can the classifier discriminate against single qualified individuals if (staying in the example) the probability of being hired is (supposed to be) independent of the applicant's gender?

asterixklang
Автор

This is not that hard if it is not selecting enough women then it is bad bot but if it is the other way around nobody gives a shit.

Amilakasun