Zobrazeno 1 - 10
of 97
pro vyhledávání: '"Rigazzi A"'
Publikováno v:
Meccanica, 2024
Combining machine learning (ML) with computational fluid dynamics (CFD) opens many possibilities for improving simulations of technical and natural systems. However, CFD+ML algorithms require exchange of data, synchronization, and calculation on hete
Externí odkaz:
http://arxiv.org/abs/2402.16196
Autor:
Balin, Riccardo, Simini, Filippo, Simpson, Cooper, Shao, Andrew, Rigazzi, Alessandro, Ellis, Matthew, Becker, Stephen, Doostan, Alireza, Evans, John A., Jansen, Kenneth E.
Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for traditional offline learning creates I/O and storage bottlenecks. Additio
Externí odkaz:
http://arxiv.org/abs/2306.12900
Autor:
Bulmer, Jacob F. F., Bell, Bryn A., Chadwick, Rachel S., Jones, Alex E., Moise, Diana, Rigazzi, Alessandro, Thorbecke, Jan, Haus, Utz-Uwe, Van Vaerenbergh, Thomas, Patel, Raj B., Walmsley, Ian A., Laing, Anthony
Publikováno v:
Sci. Adv. 8, eabl9236 (2022)
Identifying the boundary beyond which quantum machines provide a computational advantage over their classical counterparts is a crucial step in charting their usefulness. Gaussian Boson Sampling (GBS), in which photons are measured from a highly enta
Externí odkaz:
http://arxiv.org/abs/2108.01622
Autor:
Partee, Sam, Ellis, Matthew, Rigazzi, Alessandro, Bachman, Scott, Marques, Gustavo, Shao, Andrew, Robbins, Benjamin
We demonstrate the first climate-scale, numerical ocean simulations improved through distributed, online inference of Deep Neural Networks (DNN) using SmartSim. SmartSim is a library dedicated to enabling online analysis and Machine Learning (ML) for
Externí odkaz:
http://arxiv.org/abs/2104.09355
Autor:
Camargo, Juan Sebastian, Coronado, Estefanía, Ramirez, Wilson, Camps, Daniel, Deutsch, Sergi Sánchez, Pérez-Romero, Jordi, Antonopoulos, Angelos, Trullols-Cruces, Oscar, Gonzalez-Diaz, Sergio, Otura, Borja, Rigazzi, Giovanni
Publikováno v:
In Computer Networks November 2023 236
Autor:
Rigazzi, Alessandro
Data parallelism has become the de facto standard for training Deep Neural Network on multiple processing units. In this work we propose DC-S3GD, a decentralized (without Parameter Server) stale-synchronous version of the Delay-Compensated Asynchrono
Externí odkaz:
http://arxiv.org/abs/1911.02516
Autor:
Vose, Aaron, Balma, Jacob, Heye, Alex, Rigazzi, Alessandro, Siegel, Charles, Moise, Diana, Robbins, Benjamin, Sukumar, Rangan
We propose a genetic algorithm (GA) for hyperparameter optimization of artificial neural networks which includes chromosomal crossover as well as a decoupling of parameters (i.e., weights and biases) from hyperparameters (e.g., learning rate, weight
Externí odkaz:
http://arxiv.org/abs/1901.03900
Connected and Autonomous Vehicles (CAVs) will play a crucial role in next-generation Cooperative Intelligent Transportation Systems (C-ITSs). Not only is the information exchange fundamental to improve road safety and efficiency, but it also paves th
Externí odkaz:
http://arxiv.org/abs/1801.09510
Autor:
Partee, Sam, Ellis, Matthew, Rigazzi, Alessandro, Shao, Andrew E., Bachman, Scott, Marques, Gustavo, Robbins, Benjamin
Publikováno v:
In Journal of Computational Science July 2022 62
The successful deployment of safe and trustworthy Connected and Autonomous Vehicles (CAVs) will highly depend on the ability to devise robust and effective security solutions to resist sophisticated cyber attacks and patch up critical vulnerabilities
Externí odkaz:
http://arxiv.org/abs/1705.06903