Interpreting Transformers for Jet Tagging

Autor: Wang, Aaron, Gandrakota, Abhijith, Ngadiuba, Jennifer, Sahu, Vivekanand, Bhatnagar, Priyansh, Khoda, Elham E, Duarte, Javier

Machine learning (ML) algorithms, particularly attention-based transformer models, have become indispensable for analyzing the vast data generated by particle physics experiments like ATLAS and CMS at the CERN LHC. Particle Transformer (ParT), a stat

Externí odkaz: http://arxiv.org/abs/2412.03673

Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-Chip

Autor: Sun, Chang, Årrestad, Thea K., Loncar, Vladimir, Ngadiuba, Jennifer, Spiropulu, Maria

Model size and inference speed at deployment time, are major challenges in many deep learning applications. A promising strategy to overcome these challenges is quantization. However, a straightforward uniform quantization to very low precision can r

Externí odkaz: http://arxiv.org/abs/2405.00645

Efficient and Robust Jet Tagging at the LHC with Knowledge Distillation

Autor: Liu, Ryan, Gandrakota, Abhijith, Ngadiuba, Jennifer, Spiropulu, Maria, Vlimant, Jean-Roch

The challenging environment of real-time data processing systems at the Large Hadron Collider (LHC) strictly limits the computational complexity of algorithms that can be deployed. For deep learning models, this implies that only models with low comp

Externí odkaz: http://arxiv.org/abs/2311.14160

Physics Community Needs, Tools, and Resources for Machine Learning

Autor: Harris, Philip, Katsavounidis, Erik, McCormack, William Patrick, Rankin, Dylan, Feng, Yongbin, Gandrakota, Abhijith, Herwig, Christian, Holzman, Burt, Pedro, Kevin, Tran, Nhan, Yang, Tingjun, Ngadiuba, Jennifer, Coughlin, Michael, Hauck, Scott, Hsu, Shih-Chieh, Khoda, Elham E, Chen, Deming, Neubauer, Mark, Duarte, Javier, Karagiorgi, Georgia, Liu, Mia

Machine learning (ML) is becoming an increasingly important component of cutting-edge physics research, but its computational requirements present significant challenges. In this white paper, we discuss the needs of the physics community regarding ML

Externí odkaz: http://arxiv.org/abs/2203.16255

Applications and Techniques for Fast Machine Learning in Science

Autor: Deiana, Allison McCarn, Tran, Nhan, Agar, Joshua, Blott, Michaela, Di Guglielmo, Giuseppe, Duarte, Javier, Harris, Philip, Hauck, Scott, Liu, Mia, Neubauer, Mark S., Ngadiuba, Jennifer, Ogrenci-Memik, Seda, Pierini, Maurizio, Aarrestad, Thea, Bahr, Steffen, Becker, Jurgen, Berthold, Anne-Sophie, Bonventre, Richard J., Bravo, Tomas E. Muller, Diefenthaler, Markus, Dong, Zhen, Fritzsche, Nick, Gholami, Amir, Govorkova, Ekaterina, Hazelwood, Kyle J, Herwig, Christian, Khan, Babar, Kim, Sehoon, Klijnsma, Thomas, Liu, Yaling, Lo, Kin Ho, Nguyen, Tri, Pezzullo, Gianantonio, Rasoulinezhad, Seyedramin, Rivera, Ryan A., Scholberg, Kate, Selig, Justin, Sen, Sougata, Strukov, Dmitri, Tang, William, Thais, Savannah, Unger, Kai Lukas, Vilalta, Ricardo, Krosigk, Belinavon, Warburton, Thomas K., Flechas, Maria Acosta, Aportela, Anthony, Calvet, Thomas, Cristella, Leonardo, Diaz, Daniel, Doglioni, Caterina, Galati, Maria Domenica, Khoda, Elham E, Fahim, Farah, Giri, Davide, Hawks, Benjamin, Hoang, Duc, Holzman, Burt, Hsu, Shih-Chieh, Jindariani, Sergo, Johnson, Iris, Kansal, Raghav, Kastner, Ryan, Katsavounidis, Erik, Krupa, Jeffrey, Li, Pan, Madireddy, Sandeep, Marx, Ethan, McCormack, Patrick, Meza, Andres, Mitrevski, Jovan, Mohammed, Mohammed Attia, Mokhtar, Farouk, Moreno, Eric, Nagu, Srishti, Narayan, Rohin, Palladino, Noah, Que, Zhiqiang, Park, Sang Eon, Ramamoorthy, Subramanian, Rankin, Dylan, Rothman, Simon, Sharma, Ashish, Summers, Sioni, Vischia, Pietro, Vlimant, Jean-Roch, Weng, Olivia

Publikováno v: Front. Big Data 5, 787421 (2022)

In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time experimental data processing loop to accelerate scientific discovery.

Externí odkaz: http://arxiv.org/abs/2110.13041