Ali Rahimi 在 NIPS 2017 的获奖演讲
原名:Ali Rahimi's talk at NIPS(NIPS 2017 Test-of-time award presentation)
关于这个视频
Ali Rahimi 在 NIPS 2017 年 Test-of-Time 获奖演讲中指出,现代机器学习已经成为炼金术,无需严格理解即可发挥作用。他呼吁该领域更加严谨和理解。
HN 为什么推荐它:HN 指出这是对深度学习实践最尖锐、引用次数最多的批评,并且每当争论 ML 可靠性或理解时都会引用它。
“如需更尖锐、更有洞察力的评论,请观看 Ali Rahimi 在 NIPS 2017 上的简短演讲”— HN 评论 · 2018 · 原文
查看英文原文
Ali Rahimi's NIPS 2017 Test-of-Time award talk, in which he argues that modern machine learning has become alchemy, working without being rigorously understood. He calls for more rigor and understanding in the field.
Why HN likes it: HN points to it as the sharpest, most-quoted critique of deep learning practice, and cites it whenever ML reliability or understanding is debated.
“For a more cutting and insightful critique, watch Ali Rahimi's short talk at NIPS 2017”
HN 提及 4 次推荐者 3 人首次 2018最近 2025质量分 4.0
原视频频道:ObservantVids · YouTube 7.8 万次观看
演讲进阶常青深度学习咬合炼金术阿里拉希米机器学习研究










![Fun to imagine-Richard Feynman-fire[附带中文翻译字幕]](../../covers/BV1N4411S7Ec.jpg)


