PickVidsAI Ethics, Impossibility Theorems and Tradeoffs - Chris Stucchio | Crunch 2018
推荐理由
it's impossible to simultaneously treat everyone the same way, to have a useful model, and to have uniformly distributed 'bias'-free outcomes.
说明
这是2018年由CraftHub Events发布的一部演讲，主题归在AI safety, AGI & impact。它讲的是algorithmic fairness这一支里的具体问题，而不是把整个领域扫一遍。适合已经能看懂基本术语、想继续往下走的人。内容上可以概括成：Chris Stucchio presents the ethical principles behind algorithmic decision making and shows with examples from lending, criminology and education that they cannot all be satisfied at once. The talk frames AI fairness as a set of quantitative tradeoffs.这些读者给出的理由，核心是：HN cites it in algorithmic-bias threads for the impossibility result that an algorithm cannot be procedurally fair, group fair and maximally useful at once.讲法不绑某一条新闻，过几年仍然可以当材料看。从2019年到2021年，有2位不同的读者在2个不同月份把它推荐出来，其中明确叫别人去看的有0次。适合一次性看完。讲者把一个判断讲透，演示是在给这个判断配例子。如果已经会了基本定义，就把注意力放在它怎么把algorithmic fairness变成能跟着复述的例子。
视频信息
- 频道
- CraftHub Events
- 时长
- 43 分 23 秒
- 发布年份
- 2018
同主题更多
- What Happened to Horses Is Happening to Us
- Why Would AI Want to do Bad Things? Instrumental Convergence
- Veritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller Explains
- Intelligence and Stupidity: The Orthogonality Thesis
- We're building a dystopia just to make people click on ads | Zeynep Tufekci
- Intro to AI Safety, Remastered