iT邦幫忙

第 11 屆 iT 邦幫忙鐵人賽

DAY 5
0
  • Machine Learning and Human Bias

    1. Based on data (Not automatically make it neutral)
    2. Biases - Part of the technology we create in many different ways
  • Evaluating Metrics for Inclusion

  • Statistical Measurements and acceptable tradeoffs

    1. Reiterate metrics
    2. Evaluation metrics

Key things to measure how inclusive a machine learning system is

  • Equality of Opportunity

  • Simulating Decisions
    Restrict equal opportunity thresholds to invest in the best classifiers

  • Finding Errors in your dataset using Facets

Summary


上一篇
Day 04 Introduction (cont.)
下一篇
Day 06 Introduction (cont.)
系列文
ML Study Jam Journey30

尚未有邦友留言

立即登入留言