Building a physics model with fitted parameters is machine learning, but slower | Hacker News - But Better

Building a physics model with fitted parameters is machine learning, but slower harysdalvi.com

Building a physics model with fitted parameters is machine learning, but slower, and inherits its failure modes.

1 points•crackalamoo•2 days ago•0 comments•

#machine #physics #parameters #fitted #slower #machine learning #physics model #fitted parameters

0 comments

No comments yet.

Related stories

Small AI models let drones autonomously identify and attack battlefield targetsarstechnica.com
Ars Technica · 0 points · 13 days ago
An Introduction to Compression-Based Machine Learningarxiv.org
Hacker News · 2 points · 9 days ago
How To Train Interpretable Neural Networks That Accurately Extrapolate From Small Datastochasticlifestyle.com
Lobsters · 1 points · over 6 years ago
Sonic's Physics Engine... Isn't a Physics Engine?youtube.com
Lobsters · 6 points · 2 months ago
Machine-Generated, Machine-Checked Proofs for a Verified Compiler (ICFP'26) [video]youtube.com
Hacker News · 1 points · 2 days ago
Combining Machine Learning and Homomorphic Encryptionmachinelearning.apple.com
Hacker News · 1 points · 7 days ago