Skip to Content.
Sympa Menu

fizinfo - [Fizinfo] Wigner FK RMI Elméleti Osztály Szemináriuma

fizinfo AT


List archive

[Fizinfo] Wigner FK RMI Elméleti Osztály Szemináriuma

Chronological Thread 
  • From: Balog Janos <balog.janos AT>
  • To: fizinfo AT, rmkiusers AT
  • Subject: [Fizinfo] Wigner FK RMI Elméleti Osztály Szemináriuma
  • Date: Sat, 22 Jan 2022 16:45:55 +0100
  • Authentication-results: (amavisd-new); dkim=pass (1024-bit key) reason="pass (just generated, assumed good)"

Wigner FK RMI Elméleti Osztály Szemináriuma
Tisztelettel meghívjuk

Romuald Janik

"From Machine Learning to Physics, and back again..."

címmel tartandó hibrid szemináriumára.

Az előadás linkje:

Meeting ID: 913 8249 0019
Passcode: 463524


In this talk I would like to describe some fruitful interrelations between Machine Learning and Physics.
On the one hand, I will show how to use the tools of machine learning to estimate the entropy (and free energy) of a system directly from Monte Carlo configurations at a given temperature, which is commonly believed to be extremely difficult if not impossible by conventional means.
On the other hand, I will describe a proposed definition of complexity for deep neural networks, which is based on some intuitions from physics. I will show how one can use it together with a complementary notion of effective dimension to quantify the intuitive difficulty of a dataset or a learning task. These notions also reveal a rather mysterious power-law scaling during training.

Helye: RMI 2. ép médiaterem és online
Ideje: 2022 január 24 hétfő d.u. 2 óra

Szívesen látunk minden érdeklődőt.

Balog János

Archive powered by MHonArc 2.6.19+.

Top of Page