4 citations · 8 across the 2 of their papers we have counts for
3 papers
cs.LG2023★ 4 cited
Neural Architecture Search: Two Constant Shared Weights Initialisations
Ekaterina Gracheva
In the last decade, zero-cost metrics have gained prominence in neural architecture search (NAS) due to their ability to evaluate architectures without training. These metrics are…
cs.LG2021★ 4 cited
Trainless Model Performance Estimation for Neural Architecture Search
Ekaterina Gracheva
Neural architecture search has become an indispensable part of the deep learning field. Modern methods allow to find one of the best performing architectures, or to build one from…
physics.comp-ph2019
SMILES-X: autonomous molecular compounds characterization for small datasets without descriptors
Guillaume Lambard, Ekaterina Gracheva
There is more and more evidence that machine learning can be successfully applied in materials science and related fields. However, datasets in these fields are often quite small (…