TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Aequitas – An open source bias audit toolkit for machine learning

46 点作者 lainon超过 6 年前

3 条评论

opwieurposiu超过 6 年前
I find the premise that different groups should expect the same percentage of interventions highly suspect. Imagine we have a program that distributes seeing eye dogs. This toolkit would discover that sighted persons have a 0% chance of getting a dog, while blind persons have a 50% chance. Oh the injustice!
评论 #18470208 未加载
Macuyiko超过 6 年前
FairML <a href="https:&#x2F;&#x2F;github.com&#x2F;adebayoj&#x2F;fairml" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;adebayoj&#x2F;fairml</a> and algofairness <a href="https:&#x2F;&#x2F;github.com&#x2F;algofairness&#x2F;BlackBoxAuditing" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;algofairness&#x2F;BlackBoxAuditing</a> are some similar, earlier projects in the same space.
to_bpr超过 6 年前
If the goal is equity of outcome above-all-else, ignoring for any differences derived from the data, then why are we bothered investing so much time, money and effort into this area?
评论 #18469415 未加载
评论 #18469405 未加载