Podrobnosti studentského projektu

Seznam
Téma:[Deep Learning] Binary Neural Architecture Search
Katedra:Katedra kybernetiky
Vedoucí:Mgr. Oleksandr Shekhovtsov, Ph.D.
Vypsáno jako:Diplomová práce, Bakalářská práce, Semestrální projekt
Popis:Apply techniques of Bayesian Optimization to search for the configuration of a neural network giving the best validation performance, along the lines of "DARTS: Differentiable Neural Architecture Search". Of particular focus are neural networks with binary weights and activations. Experimental verification of methods developed at the department, research on the problem formulation, connection to hypergradient techniques.
Za obsah zodpovídá: Petr Pošík