Machine Learning Street Talk (MLST)
Technology
We are now sponsored by Weights and Biases! Please visit our sponsor link: http://wandb.me/MLST
Patreon: https://www.patreon.com/mlst
Yann LeCun thinks that it's specious to say neural network models are interpolating because in high dimensions, everything is extrapolation. Recently Dr. Randall Balestriero, Dr. Jerome Pesente and prof. Yann LeCun released their paper learning in high dimensions always amounts to extrapolation. This discussion has completely changed how we think about neural networks and their behaviour.
[00:00:00] Pre-intro
[00:11:58] Intro Part 1: On linearisation in NNs
[00:28:17] Intro Part 2: On interpolation in NNs
[00:47:45] Intro Part 3: On the curse
[00:48:19] LeCun
[01:40:51] Randall B
YouTube version: https://youtu.be/86ib0sfdFtw
Taming Silicon Valley - Prof. Gary Marcus
Prof. Mark Solms - The Hidden Spring
Patrick Lewis (Cohere) - Retrieval Augmented Generation
Ashley Edwards - Genie Paper (DeepMind/Runway)
Cohere's SVP Technology - Saurabh Baji
David Hanson's Vision for Sentient Robots
The Fabric of Knowledge - David Spivak
Jürgen Schmidhuber - Neural and Non-Neural AI, Reasoning, Transformers, and LSTMs
"AI should NOT be regulated at all!" - Prof. Pedro Domingos
Adversarial Examples and Data Modelling - Andrew Ilyas (MIT)
Joscha Bach - AGI24 Keynote (Cyberanimism)
Gary Marcus' keynote at AGI-24
Is ChatGPT an N-gram model on steroids?
Jay Alammar on LLMs, RAG, and AI Engineering
Can AI therapy be more effective than drugs?
Prof. Subbarao Kambhampati - LLMs don't reason, they memorize (ICML2024 2/13)
Sayash Kapoor - How seriously should we take AI X-risk? (ICML 1/13)
Sara Hooker - Why US AI Act Compute Thresholds Are Misguided
Prof. Murray Shanahan - Machines Don't Think Like Us
David Chalmers - Reality+
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
Lex Fridman Podcast
The Unbelivable Truth - Series 1 - 26 including specials and pilot