Notational Intelligence, Linus Lee | Compile 26 - YouTube
Linus Lee explores the concept of notational intelligence, examining how visual representations and symbols function as cognitive tools. By comparing traditional mathematical notations with systems developed through deep learning, the presentation investigates how artificial intelligence can help design new graphical languages to express complex, abstract concepts. Follow along using the transcript. Linus Lee explores the concept of notational intelligence, examining how visual representations and symbols function as cognitive tools. By comparing traditional mathematical notations with systems developed through deep learning, the presentation investigates how artificial intelligence can help design new graphical languages to express complex, abstract concepts. Follow along using the transcript. IBM AI Engineer Prachi Modi explains how combining neural networks for pattern recognition with symbolic AI for logic creates systems that truly understand data. This approach allows AI to move
Linus Lee, Engineer at Thrive Capital, on notational intelligence: how the ways we write ideas down shape our thinking, and how deep learning might invent entirely new notations. 00:00 Notational intelligence 01:27 What makes good notation 02:28 Abstraction 03:18 Suggestiveness and natural transformations 05:28 Graphical notation 06:27 The coordinate plane and the arrow 08:14 Programming languages as notation 09:28 Inventing new notation with deep learning 11:13 Building the toy model 13:42 The handout and training results 15:03 Invariants that make symbols meaningful 15:56 Our world vs. an…
saved by
related reading
- Notational intelligence | thesephist.comthesephist.com
- Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
- Using Artificial Intelligence to Augment Human Intelligencedistill.pub
- The World Inside Neural Networksgoodfire.ai
- AI Is Learning at the Wrong Level of Abstraction — Matthieu Wyartyoutube.com
- What Would Non-Linear Features Actually Look Like? — Liv Gortonlivgorton.com
- What is the purpose of interpretability?ericjmichaud.com
- The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
- Understanding is the new bottleneck — Geoffrey Litt, Notionyoutube.com
- A Theory of Deep Learning | Elements of a Vector Spaceelonlit.com
- Yann LeCun: World Models: Enabling the next AI revolutionyoutube.com
- Structure and Interpretation of Deep Networkssidn.baulab.info