no code implementations • 25 Mar 2024 • Nikita Durasov, Doruk Oner, Jonathan Donier, Hieu Le, Pascal Fua
Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance.
no code implementations • 28 Sep 2021 • Nikita Durasov, Artem Lukoyanov, Jonathan Donier, Pascal Fua
Graph Neural Networks (GNNs) can predict the performance of an industrial design quickly and accurately and be used to optimize its shape effectively.
no code implementations • 22 Sep 2021 • Subeesh Vasu, Nicolas Talabot, Artem Lukoianov, Pierre Baqué, Jonathan Donier, Pascal Fua
Deep implicit surfaces excel at modeling generic shapes but do not always capture the regularities present in manufactured objects, which is something simple geometric primitives are particularly good at.
no code implementations • 11 Mar 2019 • Jonathan Donier
Following the recent work on capacity allocation, we formulate the conjecture that the shattering problem in deep neural networks can only be avoided if the capacity propagation through layers has a non-degenerate continuous limit when the number of layers tends to infinity.
no code implementations • 22 Feb 2019 • Jonathan Donier
In the highly non-linear limit where decoupling is total, we show that the propagation of capacity throughout the layers follows a simple markovian rule, which turns into a diffusion PDE in the limit of deep networks with residual layers.
no code implementations • 12 Feb 2019 • Jonathan Donier
We focus more particularly on spatial capacity allocation, which analyzes a posteriori the effective number of parameters that a given model has allocated for modelling dependencies on a given point or region in the input space, in linear settings.