Papers of the day   All papers

Deep learning of dynamical attractors from time series measurements

Comments

William Gilpin: My new preprint explores using neural networks to learn โ€œstrange attractorsโ€ from time series. If we measure a complex system over time, can we infer additional measurement dimensions & discover underlying structure? (1/N) https://arxiv.org/abs/2002.05909 https://t.co/iFRiZE6c3R

10 replies, 923 likes


Richard Gao: This looks fantastic! But also goddamnit.

2 replies, 10 likes


Chico Camargo: Neural networks are great at finding patterns. But what if the pattern is CHAOS? Can neural networks learn chaotic behaviour? Paper and thread.

0 replies, 7 likes


Dr Simon Osindero: This looks really neat! Looking forward to taking a closer look when I get a chance. Takenโ€™s embedding theorem meets deep learning FTW ๐Ÿ‘๐Ÿฝ.

0 replies, 6 likes


Andre Brown: Cool! Now do worm data! @_mlechha @greg_stephens https://arxiv.org/abs/1911.10559

0 replies, 5 likes


๐Š๐ž๐ง๐ฃ๐ข ๐‹๐ž๐ž: Amazing work! One of those rare papers that you have to read immediately and put off the end of the work day for.

1 replies, 4 likes


Content

Found on Feb 17 2020 at https://arxiv.org/pdf/2002.05909.pdf

PDF content of a computer science paper: Deep learning of dynamical attractors from time series measurements