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
#103 - Prof. Edward Grefenstette - Language, Semantics, Philosophy
#102 - Prof. MICHAEL LEVIN, Prof. IRINA RISH - Emergence, Intelligence, Transhumanism
#100 Dr. PATRICK LEWIS (co:here) - Retrieval Augmented Generation
#99 - CARLA CREMER & IGOR KRAWCZUK - X-Risk, Governance, Effective Altruism
[NO MUSIC] #98 - Prof. LUCIANO FLORIDI - ChatGPT, Singularitarians, Ethics, Philosophy of Information
#98 - Prof. LUCIANO FLORIDI - ChatGPT, Superintelligence, Ethics, Philosophy of Information
#97 SREEJAN KUMAR - Human Inductive Biases in Machines from Language
#96 Prof. PEDRO DOMINGOS - There are no infinities, utility functions, neurosymbolic
#95 - Prof. IRINA RISH - AGI, Complex Systems, Transhumanism
#94 - ALAN CHAN - AI Alignment and Governance #NEURIPS
#93 Prof. MURRAY SHANAHAN - Consciousness, Embodiment, Language Models
#92 - SARA HOOKER - Fairness, Interpretability, Language Models
#91 - HATTIE ZHOU - Teaching Algorithmic Reasoning via In-context Learning #NeurIPS
(Music Removed) #90 - Prof. DAVID CHALMERS - Consciousness in LLMs [Special Edition]
#90 - Prof. DAVID CHALMERS - Consciousness in LLMs [Special Edition]
#88 Dr. WALID SABA - Why machines will never rule the world [UNPLUGGED]
#86 - Prof. YANN LECUN and Dr. RANDALL BALESTRIERO - SSL, Data Augmentation, Reward isn't enough [NEURIPS2022]
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
#84 LAURA RUIS - Large language models are not zero-shot communicators [NEURIPS UNPLUGGED]
#83 Dr. ANDREW LAMPINEN (Deepmind) - Natural Language, Symbols and Grounding [NEURIPS2022 UNPLUGGED]
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
Elliot in the Morning