talgatdaulbaev

Talgat Daulbaev

Professor: Andrzej Cichoki

Graduated from: Lomonosov Moscow State University

Research interests: Deep Learning, Dynamical Systems, Numerical Linear Algebra

Thesis title: Applications of Dynamical Systems for Deep Learning

Publications:

Accepted:

  • Katrutsa A., Daulbaev T., Oseledets I. Black-box learning of multigrid parameters //Journal of Computational and Applied Mathematics. – 2019. – С. 112524.

To be submitted: 

  • Active Subspace of Neural Networks: Structural Analysis and Universal Attacks // Cui C., Zhang K., Daulbaev T., Gusak J., Oseledets I., Zhang Z.
  • Reduced-Order Modeling of Deep Neural Networks” // Gusak J, Daulbaev T., Ponomarev E., Cichocki A., Oseledets I.

Conferences:

  • International Workshop on Tensor Networks and Machine Learning (Moscow, 2018) • Matrix Methods in Mathematics and Applcations (Moscow, 2019)

 

 

Deep Multigrid: learning prolongation and restriction matrices