The @karpathy interview
0:00:00 – AGI is still a decade away
0:30:33 – LLM cognitive deficits
0:40:53 – RL is terrible
0:50:26 – How do humans learn?
1:07:13 – AGI will blend into 2% GDP growth
1:18:24 – ASI
1:33:38 – Evolution of intelligence & culture
1:43:43 - Why self driving took so long
1:57:08 - Future of education
Look up Dwarkesh Podcast on YouTube, Apple Podcasts, Spotify, etc. Enjoy!
Our next #robustoptimizationwebinar takes place this Friday, December 1, at 15:00 (CET).
Speaker 1: @_estherjulien (TU Delft)
Speaker 2: Justin Dumouchelle (University of Toronto)
#ROW
For more information check our webpage:
https://t.co/5AiEHKL75P
Thursday at 12pm Poster Session
Neur2SP: Neural Two-Stage Stochastic Programming
with Justin Dumouchelle, @Rpatel_15, @meurevine
https://t.co/6yWkrLldl6
Train a ReLU network to approximate a complex expected value in a 2-stage stoch. program -> fast near-optimal solutions!
If you're at #NeurIPS2022 and interested in ML-for-Optimization, please check out my students and collaborators' poster presentations; a brief overview ⬇️
Extremely happy to share that Neur2SP: Neural Two Stage Stochastic Program, joint work with @jsdumouchelle, @lyeskhalil and @meurevine got accepted at #NeurIPS2022. The journey of Neur2SP from a course project to #NeurIPS2022 was pretty exciting. [1/3]
We train Neural Nets with ReLU activation to predict the second stage cost function of two-stage stochastic programs.
It helps in formulating a problem structure agnostic surrogate MIP to quickly find a good feasible solution. [2/3]
I am excited to share my latest work: 8-bit optimizers – a replacement for regular optimizers. Faster 🚀, 75% less memory 🪶, same performance📈, no hyperparam tuning needed 🔢. 🧵/n
Paper: https://t.co/V5tjOmaWvD
Library: https://t.co/JAvUk9hrmM
Video: https://t.co/TWCNpCtCap
Our paper "Pest management in cotton farms: an AI-system case study from the global South" has been accepted in KDD 2020. We describe a new solution for pest monitoring using AI & share the lessons we learned. 1/n
📰Paper: https://t.co/fikeqy8meB
📹Video: https://t.co/ci1W1gaLre
I successfully defended my Master's thesis today on "Decision Making Under Uncertainty Using Machine Learning". I would like to thank my advisors, @69alodi and #YoshuaBengio, for giving me this opportunity.