1 code implementation • 3 Oct 2023 • Roberto L. Castro, Andrei Ivanov, Diego Andrade, Tal Ben-Nun, Basilio B. Fraguela, Torsten Hoefler
We present the V:N:M format, which enables the execution of arbitrary N:M ratios on SPTCs.
no code implementations • 23 Aug 2023 • Julia Bazinska, Andrei Ivanov, Tal Ben-Nun, Nikoli Dryden, Maciej Besta, Siyuan Shen, Torsten Hoefler
Graph Neural Networks (GNNs) are a powerful tool for handling structured graph data and addressing tasks such as node classification, graph classification, and clustering.
1 code implementation • 30 Jul 2023 • Andrei Ivanov, Stefan Maria Ailuro
Polynomial regression is widely used and can help to express nonlinear patterns.
no code implementations • 15 Apr 2023 • Andrei Ivanov, Nikoli Dryden, Tal Ben-Nun, Saleh Ashkboos, Torsten Hoefler
As deep learning models grow, sparsity is becoming an increasingly critical component of deep neural networks, enabling improved performance and reduced storage.
1 code implementation • 20 Oct 2021 • Oliver Rausch, Tal Ben-Nun, Nikoli Dryden, Andrei Ivanov, Shigang Li, Torsten Hoefler
Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute.
no code implementations • 1 Jan 2021 • Andrei Ivanov, Anna Golovkina
The paper addresses a problem of abnormalities detection in nonlinear processes represented by measured time series.
no code implementations • 7 Jul 2020 • Andrei Ivanov, Ilya Agapov
This paper presents a novel approach for constructing neural networks which model charged particle beam dynamics.
1 code implementation • 30 Jun 2020 • Andrei Ivanov, Nikoli Dryden, Tal Ben-Nun, Shigang Li, Torsten Hoefler
Transformers are one of the most important machine learning workloads today.
no code implementations • 24 May 2020 • Andrei Ivanov, Uwe Iben, Anna Golovkina
This paper discusses an approach for incorporating prior physical knowledge into the neural network to improve data efficiency and the generalization of predictive models.
no code implementations • 19 Dec 2019 • Andrei Ivanov, Anna Golovkina, Uwe Iben
The connection of Taylor maps and polynomial neural networks (PNN) to solve ordinary differential equations (ODEs) numerically is considered.
1 code implementation • 16 Aug 2019 • Andrei Ivanov, Sergei Andrianov
The weights of the network can be directly calculated from the equation.
no code implementations • 5 Feb 2018 • Andrei Ivanov, Alena Sholokhova, Sergei Andrianov, Roman Konoplev-Esgenburg
We also demonstrate an interpretation of the fitted neural network by converting it to a system of differential equations.