On the Learnability of Physical Concepts: Can a Neural Network Understand What’s Real?

N/A

On the Learnability of Physical Concepts: Can a Neural Network Understand What’s Real? Alessandro Achille Stefano Soatto AWS AI Labs arXiv:2207.12186v2 [cs.LG] 4 Aug 2022 April 13, 2022 (revised July 13, 2022)…

saved by

• Umangi Jain

related reading

• proceedings.mlr.press/v202/ma23a/ma23a.pdfproceedings.mlr.press
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Toy Models of Superpositiontransformer-circuits.pub
• NL.pdfabehrouz.github.io
• pdfopenreview.net
• The Building Blocks of Interpretabilitydistill.pub
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• There Will Be a Scientific Theory of Deep Learningarxiv.org
• Understanding deep learning requires rethinking generalizationarxiv.org
• [2508.11214] How Causal Abstraction Underpins Computational Explanationarxiv.org
• You can’t imitation-learn how to continual-learn — LessWronglesswrong.com
• arxiv.org/pdf/1805.08522arxiv.org