Asynchronous Stochastic Gradient Descent with Decoupled Backpropagation and Layer-Wise Updates

Autor: Fokam, Cabrel Teguemne, Nazeer, Khaleelulla Khan, König, Lukas, Kappel, David, Subramoney, Anand

The increasing size of deep learning models has created the need for more efficient alternatives to the standard error backpropagation algorithm, that make better use of asynchronous, parallel and distributed computing. One major shortcoming of backp

Externí odkaz: http://arxiv.org/abs/2410.05985

New Measurements of the Deuteron to Proton F2 Structure Function Ratio

Autor: Biswas, Debaditya, Gonzalez, Fernando Araiza, Henry, William, Karki, Abishek, Morean, Casey, Nadeeshani, Sooriyaarachchilage, Sun, Abel, Abrams, Daniel, Ahmed, Zafar, Aljawrneh, Bashar, Alsalmi, Sheren, Ambrose, George, Armstrong, Whitney, Asaturyan, Arshak, Assumin-Gyimah, Kofi, Gayoso, Carlos Ayerbe, Bandari, Anashe, Basnet, Samip, Berdnikov, Vladimir, Bhatt, Hem, Bhetuwal, Deepak, Boeglin, Werner, Bosted, Peter, Brash, Edward, Bukhari, Masroor, Chen, Haoyu, Chen, Jian-Ping, Chen, Mingyu, Christy, Michael Eric, Dusa, Silviu Covrig, Craycraft, Kayla, Danagoulian, Samuel, Day, Donal, Diefenthaler, Markus, Dlamini, Mongi, Dunne, James, Duran, Burcu, Dutta, Dipangkar, Ent, Rolf, Evans, Rory, Fenker, Howard, Fomin, Nadia, Fuchey, Eric, Gaskell, David, Gautam, Thir Narayan, Hansen, Jens-Ole, Hauenstein, Florian, Hernandez, A., Horn, Tanja, Huber, Garth, Jones, Mark, Joosten, Sylvester, Kabir, Md Latiful, Keppel, Cynthia, Khanal, Achyut, King, Paul, Kinney, Edward, Kohl, Michael, Lashley-Colthirst, Nathaniel, Li, Shujie, Li, Wenliang, Liyanage, Anusha Habarakada, Mack, David, Malace, Simona, Markowitz, Pete, Matter, John, Meekins, David, Michaels, Robert, Mkrtchyan, Arthur, Mkrtchyan, Hamlet, Moore, Zae, Nazeer, S. J., Nanda, Shirsendu, Niculescu, Gabriel, Niculescu, Maria, Nguyen, Huong, Nuruzzaman, Nuruzzaman, Pandey, Bishnu, Park, Sanghwa, Pooser, Eric, Puckett, Andrew, Rehfuss, Melanie, Reinhold, Joerg, Sawatzky, Bradley, Smith, G., Szumila-Vance, Holly, Tadepalli, Arun, Tadevosyan, Vardan, Trotta, Richard, Wood, Stephen, Yero, Carlos, Zhang, Jinlong

Nucleon structure functions, as measured in lepton-nucleon scattering, have historically provided a critical observable in the study of partonic dynamics within the nucleon. However, at very large parton momenta it is both experimentally and theoreti

Externí odkaz: http://arxiv.org/abs/2409.15236

A comparative analysis of preamble sequences for Galvanic Coupling Intra-Body Communications

Autor: Kulsoom, Farzana, Savazzi, Pietro, Dell'Acqua, Fabio, Chaudhry, Hassan Nazeer, Vizziello, Anna

Galvanic coupled-intra-body communication (GC-IBC) is an innovative research area contributing to transform personalized medicine by enabling seamless connectivity and communication among implanted devices. To establish a reliable communication link

Externí odkaz: http://arxiv.org/abs/2407.01195

Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models

Autor: Mukherji, Rishav, Schöne, Mark, Nazeer, Khaleelulla Khan, Mayr, Christian, Kappel, David, Subramoney, Anand

Activity and parameter sparsity are two standard methods of making neural networks computationally more efficient. Event-based architectures such as spiking neural networks (SNNs) naturally exhibit activity sparsity, and many methods exist to sparsif

Externí odkaz: http://arxiv.org/abs/2405.00433

Language Modeling on a SpiNNaker 2 Neuromorphic Chip

Autor: Nazeer, Khaleelulla Khan, Schöne, Mark, Mukherji, Rishav, Vogginger, Bernhard, Mayr, Christian, Kappel, David, Subramoney, Anand

As large language models continue to scale in size rapidly, so too does the computational power required to run them. Event-based networks on neuromorphic devices offer a potential way to reduce energy consumption for inference significantly. However

Externí odkaz: http://arxiv.org/abs/2312.09084