Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Pol Adrian"'
Autor:
Trautmann, Dietrich, Ostapuk, Natalia, Grail, Quentin, Pol, Adrian Alan, Bonifazi, Guglielmo, Gao, Shang, Gajek, Martin
In high-stakes domains like legal question-answering, the accuracy and trustworthiness of generative AI systems are of paramount importance. This work presents a comprehensive benchmark of various methods to assess the groundedness of AI-generated re
Externí odkaz:
http://arxiv.org/abs/2410.08764
Autor:
Pol, Adrian Alan, Govorkova, Ekaterina, Gronroos, Sonja, Chernyavskaya, Nadezda, Harris, Philip, Pierini, Maurizio, Ojalvo, Isobel, Elmer, Peter
Unsupervised deep learning techniques are widely used to identify anomalous behaviour. The performance of such methods is a product of the amount of training data and the model size. However, the size is often a limiting factor for the deployment on
Externí odkaz:
http://arxiv.org/abs/2310.06047
Autor:
Tsoi, Ho Fung, Pol, Adrian Alan, Loncar, Vladimir, Govorkova, Ekaterina, Cranmer, Miles, Dasu, Sridhara, Elmer, Peter, Harris, Philip, Ojalvo, Isobel, Pierini, Maurizio
Publikováno v:
EPJ Web of Conferences 295, 09036 (2024)
The high-energy physics community is investigating the potential of deploying machine-learning-based solutions on Field-Programmable Gate Arrays (FPGAs) to enhance physics sensitivity while still meeting data processing time constraints. In this cont
Externí odkaz:
http://arxiv.org/abs/2305.04099
Autor:
Zandonati, Ben, Bucagu, Glenn, Pol, Adrian Alan, Pierini, Maurizio, Sirkin, Olya, Kopetz, Tal
Model compression is instrumental in optimizing deep neural network inference on resource-constrained hardware. The prevailing methods for network compression, namely quantization and pruning, have been shown to enhance efficiency at the cost of perf
Externí odkaz:
http://arxiv.org/abs/2302.07612
Model compression is vital to the deployment of deep learning on edge devices. Low precision representations, achieved via quantization of weights and activations, can reduce inference time and memory requirements. However, quantifying and predicting
Externí odkaz:
http://arxiv.org/abs/2210.08502
Autor:
Pol, Adrian Alan, Aarrestad, Thea, Govorkova, Ekaterina, Halily, Roi, Klempner, Anat, Kopetz, Tal, Loncar, Vladimir, Ngadiuba, Jennifer, Pierini, Maurizio, Sirkin, Olya, Summers, Sioni
We apply object detection techniques based on deep convolutional blocks to end-to-end jet identification and reconstruction tasks encountered at the CERN Large Hadron Collider (LHC). Collision events produced at the LHC and represented as an image co
Externí odkaz:
http://arxiv.org/abs/2202.04499
Autor:
Tsoi, Ho Fung1 ho.fung.tsoi@cern.ch, Pol, Adrian Alan2, Loncar, Vladimir3,4, Govorkova, Ekaterina3, Cranmer, Miles2,5, Dasu, Sridhara1, Elmer, Peter2, Harris, Philip3, Ojalvo, Isobel2, Pierini, Maurizio6
Publikováno v:
EPJ Web of Conferences. 5/6/2024, Vol. 295, p1-9. 9p.
Autor:
Govorkova, Ekaterina, Puljak, Ema, Aarrestad, Thea, James, Thomas, Loncar, Vladimir, Pierini, Maurizio, Pol, Adrian Alan, Ghielmetti, Nicolò, Graczyk, Maksymilian, Summers, Sioni, Ngadiuba, Jennifer, Nguyen, Thong Q., Duarte, Javier, Wu, Zhenbin
Publikováno v:
Nature Machine Intelligence 4, 154 (2022)
In this paper, we show how to adapt and deploy anomaly detection algorithms based on deep autoencoders, for the unsupervised detection of new physics signatures in the extremely challenging environment of a real-time event selection system at the Lar
Externí odkaz:
http://arxiv.org/abs/2108.03986
Autor:
Pol, Adrian Alan, Aarrestad, Thea, Govorkova, Katya, Halily, Roi, Klempner, Anat, Kopetz, Tal, Loncar, Vladimir, Ngadiuba, Jennifer, Pierini, Maurizio, Sirkin, Olya, Summers, Sioni
We apply object detection techniques based on Convolutional Neural Networks to jet reconstruction and identification at the CERN Large Hadron Collider. In particular, we focus on CaloJet reconstruction, representing each event as an image composed of
Externí odkaz:
http://arxiv.org/abs/2105.05785
Autor:
Fahim, Farah, Hawks, Benjamin, Herwig, Christian, Hirschauer, James, Jindariani, Sergo, Tran, Nhan, Carloni, Luca P., Di Guglielmo, Giuseppe, Harris, Philip, Krupa, Jeffrey, Rankin, Dylan, Valentin, Manuel Blanco, Hester, Josiah, Luo, Yingyi, Mamish, John, Orgrenci-Memik, Seda, Aarrestad, Thea, Javed, Hamza, Loncar, Vladimir, Pierini, Maurizio, Pol, Adrian Alan, Summers, Sioni, Duarte, Javier, Hauck, Scott, Hsu, Shih-Chieh, Ngadiuba, Jennifer, Liu, Mia, Hoang, Duc, Kreinar, Edward, Wu, Zhenbin
Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drasticall
Externí odkaz:
http://arxiv.org/abs/2103.05579