Links of interest
Dear all, I just wanted to share some links which could be of interest (and thx to Philip and August for the references here).
1) A school in Germany which could be of interest, see https://www.fz-juelich.de/en/ias/jsc/education/master-students/guest-student-programme
2) A hot software, if you love Pandas, PandasAI is magic, see https://www.pandabi.ai/auth/sign-in. The API is free and it is just cool!
3) From Philip Hoel, this video is very very interesting, extracting physical laws from ML, see
https://www.youtube.com/watch?v=fk2r8y5TfNY (Miles Cranmer - The next great scientific theory is hiding inside a neural network)
4) On combinatorial optimization and graph neural networks (text in Norwegian from August Femtehjell).
Ising formuleringer av NP-problemer designet for kvanteoptimering. Disse formuleringene egner seg godt som loss funksjoner for å måle hvor bra optimeringsproblemet er løst, uten å vite den sanne løsningen:
https://arxiv.org/abs/1302.5843
Anvendelse av noen av disse formuleringene for graf nevrale nettverk (GNN):
https://www.nature.com/articles/s42256-022-00468-6
GNN kombinert med heurestikker for grafproblemer:
https://bora.uib.no/bora-xmlui/handle/11250/3043799
En pakke fra Google Deepmind for å implementere GNN med JAX, som inneholder et par forskjellige eksempler:
https://github.com/google-deepmind/jraph/tree/master
Supervised trening av GNN for å løse Traveling Salesman, som tydeliggjør noen av problemene med å løse NP problemer supervised:
If you come across interesting links you would like to share, do not hesitate to do so.
best wishes to all,
Morten