To solve PDEs, you can learn at a fixed resolution (e.g. with U-net) and interpolate. But error cannot be arbitrarily small this way. Our neural operators are guaranteed to approximate arbitrarily well at any resolution since they learn in function space https://
arxiv.org/abs/2108.08481
INNOVATION
-
Neural Operators for PDEs: Resolution-Independent Function Space Learning
By
–
-
FastAI Students Explain Diffusion Model Paper
By
–
Another great diffusion model paper explainer from our wonderful @fastdotai students!
-
NVIDIA Internship: Computer Vision and AI for Autonomous Driving
By
–
Come intern with us at @nvidia We collaborate with @ALVAREZ_JOSEM team to build full-stack computer vision and AI models with applications in autonomous driving,e.g https://
arxiv.org/abs/2204.12451 @ZhidingYu @voidrank -
Engineer’s Weekend DIY Bubble Machine Project Showcases Creative Innovation
By
–
When engineers get bored during the weekend 😃
— Pascal Bornet (@pascal_bornet) 8 décembre 2022
DIY bubble machine. Stellar work! What upgrades would you make?
Created by animator and filmmaker Rafael Sommerhalder
Credit: C. Carter#engineering #creativity #innovation pic.twitter.com/bLa5W2xQxzWhen engineers get bored during the weekend DIY bubble machine. Stellar work! What upgrades would you make? Created by animator and filmmaker Rafael Sommerhalder Credit: C. Carter
#engineering #creativity #innovation -
Predictions now continue running after closing browser tab
By
–
A little fix for you power users: when you run a model through the website and close the tab, it no longer stops the prediction. Now you can spin off a bunch of long-running predictions, go get coffee, then come back to your dashboard later to see them finished.
-
AI Debate 3 Reaches 14,694 Attendees, Aims for 100,000
By
–
AI DEBATE 3: Already 14,694 Attendees! Let's make HISTORY. Let's reach 100,000 attendees: Invite your LinkedIn network to #AGIDebate ! LinkedIn: https://
linkedin.com/events/aidebat
e3-thisisthe2021debateth6796651928362221568/
… #AGI #AIDebate #MontrealAI #WeAreAGI -
Zero-shot Super-resolution Tests for Neural Operators Benchmark
By
–
But it is crucial to add zero-shot super-resolution tests. Neural operators can output at any resolution since they learn mappings between function spaces, but U-Nets cannot. Can u please add these tests to the benchmark? @rejuvyesh @jo_brandstetter
-
CockroachDB Alum Founder Launches New Venture
By
–
you might think that they are ngmi but dont be fooled their founder is cockroachdb alum gmi
-
New Database Trends: TigerBeetle, Redpanda, DuckDB Dominate
By
–
haha your “new DBs” are all like 4-5 years old… the hot stuff now is tigerbeetle redpanda and duckdb basically if your database doesnt have a animal name you are ngmi
-
Google and Lund University’s Optimus Learns Optimization Architecture
By
–
Google & Lund U’s Optimus Learned Optimization Architecture Efficiently Captures Complex Dependencies https://
syncedreview.com/2022/12/07/goo
gle-lund-us-optimus-learned-optimization-architecture-efficiently-captures-complex-dependencies/
…