Richard Sutton等批评深度学习:需彻底重构而非微调

Seismic! “current deep learning methods are weak and inefficient, and need not more tweaks, but fun...

精选理由

AI大佬组团开怼现有深度学习:Sutton和Marcus联手发论文说光调参没用,得从头改架构,还搞了个新公司Oak Lab。想了解AI前沿争议的可以看看。

AI 摘要

Richard Sutton、Gary Marcus和Khurram Javed等AI学者公开批评当前深度学习方法弱且低效,认为需要根本性新想法和彻底重做,而非简单调整。Sutton与John Carmack的Keen Technologies合作后,现在与Javed共同创立新公司Oak Lab,专注强化学习(RL)和运行时经验驱动的智能。Marcus自2018年发表论文《Deep learning: A Critical Appraisal》以来持续持类似观点,该论文曾被Yann LeCun指责为“大多错误”。Oak Lab强调智能来自持续交互经验,与主流深度学习路径分道扬镳。

原文 · Gary Marcus

Seismic! “current deep learning methods are weak and inefficient, and need not more tweaks, but fun...

Seismic! “current deep learning methods are weak and inefficient, and need not more tweaks, but fundamentally new ideas and a thorough reworking before they can provide a solid foundation for achieving the more ambitious goals of AI” — incredible to see @RichardSutton so forcefully affirm what I have been saying since 2018, in “Deep learning: A Critical Appraisal” an arXiv paper that @ylecun once alleged was “mostly wrong”. Richard Sutton @RichardSSutton I can’t say enough good things about John Carmack @ID_AA_Carmack and his Keen Technologies. But now Khurram Javed @kjaved_ and I have broken away to start our own startup and pursue a slightly different path toward understanding intelligence. Like Keen (and like Ineffable) we at Oak Lab @oaklab_ai believe in reinforcement learning and that intelligence is created and maintained from run-time experience. But we think current deep learning methods are weak and inefficient, and need not more tweaks, but fundamentally new ideas and a thorough reworking before they can provide a solid foundation for achieving the more ambitious goals of AI. 🔗 View Quoted Tweet 💬 5 🔄 5 ❤️ 28 👀 3216 📊 7 ⚡