• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site


Physics inspired Machine Learning

*recommended age
Event ended
During two days of the workshop "Physics inspired Machine Learning", organized by the Center for Deep Learning and Bayesian Methods and the Laboratory of Methods for Big Data Analysis (LAMBDA), we will discuss how to benefit from the exchange of ideas between representatives of data science, in particular, machine learning, and traditional sciences, in particular, physics. Researchers from HSE and other institutions will present their research results. Scientists at the University of Arizona, the University of Milan, NIISI RAS, P.N. Lebedev Physical Institute of the Russian Academy of Sciences, Moscow State University, Skoltech.

Physics inspired Machine Learning

Dates: January, 20-21, 2020
Location: Pokrovsky boulevard,11
Language: Russian
Materials: Video

January, 20, room R 208

12.10 – 12.50
Generative Models in Particle Physics 
Denis Derkach, NRU HSE

12.50 – 14.00
From Spin Glasses to Neural Networks
Riccardo Fabbricatore, University of Milan

14.05 – 14.55
Combinatorial and Neural Graph Vector Representations
for Graph Isomorphism and Classification
Evgeny Burnaev, Skoltech                                

15.40 – 16.05
Neural ODE and Hamiltonian Systems
Alexandra Volokhova, NRU HSE                                       

16.05 – 16.30
Hamiltonian Flows
Viktor Oganesian, NRU HSE                                                      

16.30 – 16.55
Implicit MCMC
Evgeny Egorov, Skoltech

17.00 – 18.00
Interpretable & Tractable Machine Learning for Natural
and Engineering Sciences
Michael Chertkov, University of Arizona 

January, 21, Small Conference Room of Cultural Center (Z)

11.00 – 12.10
n-neighborhood Method for Computing Free Energy
Leonid Litinskii, NIISI RAS                                                       

12.10 –12.50
Open ML challenges for High-Energy Physics experiments
Andrey Ustyuzhanin, NRU HSE         

13.00 – 14.30
Statistical Physics and Reconstruction Noisy Patterns
Andrey Leonidov, P.N. Lebedev Physical Institute of the Russian Academy of Sciences                                           

15.30 – 16.20
Hamiltonian Networks & Model-Based RL
Dmitry Kropotov, NRU HSE, MSU