all AI news
061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Jan. 4, 2022, 12:24 p.m. | Machine Learning Street Talk
Machine Learning Street Talk www.youtube.com
Yann LeCun thinks that it's specious to say neural network models are interpolating because in high dimensions, everything is extrapolation. Recently Dr. Randall Bellestrerio, 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 …
More from www.youtube.com / Machine Learning Street Talk
Connor Leahy - e/acc, AGI and the future.
3 days, 20 hours ago |
www.youtube.com
LESSONS FROM BIOLOGY ABOUT BUILDING AGI.
2 weeks, 3 days ago |
www.youtube.com
TacticAI: an AI assistant for football tactics
2 weeks, 4 days ago |
www.youtube.com
There is no distinction between data and code! #tech
3 weeks, 2 days ago |
www.youtube.com
WE MUST ADD STRUCTURE TO DEEP LEARNING BECAUSE...
3 weeks, 2 days ago |
www.youtube.com
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Alternant Data Engineering
@ Aspire Software | Angers, FR
Senior Software Engineer, Generative AI
@ Google | Dublin, Ireland