[seqfan] Using AI to help Superseeker guess formulas for sequences

Neil Sloane njasloane at gmail.com
Sat Oct 3 22:46:07 CEST 2020

Dear Seq Fans, I keep coming across sequences that badly need a formula,
possibly expressing them in terms of some known sequence.
A337641 and A337655 are two recent examples.

Why not use AI to strengthen Superseeker?, I keep saying

There is a talk on Monday that might be relevant: This announcement just
arrived in email:

Springer Nature <springernature at newsletter.springernature.com>
George Em Karniadakis (Brown University and MIT)
>From PINNs to DeepOnets: Approximating functions, functionals, and
operators using deep neural networks

 Throughout October, authors from the new journal SN Partial Differential
Equations and Applications will be hosting a series of free webinars on
topics related to partial differential equations.

Up next is a presentation by George Em Karniadakis of Brown University and
MIT on approximating functions using deep neural networks. Join us for a
lively discussion on October 5th at 9am EST, 3pm CET.
I signed up, but AI and PDEs are  not my field.

If anyone is interested, please watch too

Best regards

Neil J. A. Sloane, President, OEIS Foundation.
11 South Adelaide Avenue, Highland Park, NJ 08904, USA.
Also Visiting Scientist, Math. Dept., Rutgers University, Piscataway, NJ.
Phone: 732 828 6098; home page: http://NeilSloane.com
Email: njasloane at gmail.com

More information about the SeqFan mailing list