Zobrazeno 1 - 10
of 180
pro vyhledávání: '"Alp, Emre"'
Recent work has shown that 8-bit floating point (FP8) can be used for efficiently training neural networks with reduced computational overhead compared to training in FP32/FP16. In this work, we investigate the use of FP8 training in a federated lear
Externí odkaz:
http://arxiv.org/abs/2407.02610
We propose a novel training recipe for federated learning with heterogeneous networks where each device can have different architectures. We introduce training with a side objective to the devices of higher complexities to jointly train different arc
Externí odkaz:
http://arxiv.org/abs/2207.03031
Autor:
Alp, Emre, Olivieri, Federico, Aulitto, Martina, Castaldo, Rachele, Contursi, Patrizia, Cocca, Mariacristina, Gentile, Gennaro
Publikováno v:
In Surfaces and Interfaces December 2024 55
Autor:
Acar, Durmus Alp Emre, Zhao, Yue, Navarro, Ramon Matas, Mattina, Matthew, Whatmough, Paul N., Saligrama, Venkatesh
We propose a novel federated learning method for distributively training neural network models, where the server orchestrates cooperation between a subset of randomly chosen devices in each round. We view Federated Learning problem primarily from a c
Externí odkaz:
http://arxiv.org/abs/2111.04263
Autor:
Siahkamari, Ali, Acar, Durmus Alp Emre, Liao, Christopher, Geyer, Kelly, Saligrama, Venkatesh, Kulis, Brian
The task of approximating an arbitrary convex function arises in several learning problems such as convex regression, learning with a difference of convex (DC) functions, and learning Bregman or $f$-divergences. In this paper, we develop and analyze
Externí odkaz:
http://arxiv.org/abs/2111.01348
Publikováno v:
In Materials Science & Engineering B June 2024 304
Autor:
GUNDEMIR, Migena Gjoni1, YILDIZ, Alp Emre2, BUYUKUNAL, Serkan Kemal2, MURATOGLU, Karlo2, OZKAN, Ermiş3, DEMIRCIOGLU, Aysegul4, CHOUDHARY, Om Prakash5 om.choudhary@gadvasu.in, GUZEL, Baris Can6
Publikováno v:
Kafkas Universitesi Veteriner Fakultesi Dergisi. Jan/Feb2024, Vol. 30 Issue 1, p87-94. 8p.
Autor:
Migena Gjoni GUNDEMIR, Alp Emre YILDIZ, Serkan Kemal BUYUKUNAL, Karlo MURATOGLU, Ermiş OZKAN, Aysegul DEMIRCIOGLU, Om Prakash CHOUDHARY, Baris Can GUZEL
Publikováno v:
Kafkas Universitesi Veteriner Fakültesi Dergisi, Vol 30, Iss 1, Pp 87-94 (2023)
Carcass discrimination is a very important issue in the evaluation of different sheep breeds as lamb meat for the red meat sector and the study aims to determine the carcass differences of Romanov and Kıvırcık lambs up to 6 months old by 2D geomet
Externí odkaz:
https://doaj.org/article/55e0a0b08d7446a480193fb0e7cb831d
Conventional machine learning applications in the mobile/IoT setting transmit data to a cloud-server for predictions. Due to cost considerations (power, latency, monetary), it is desirable to minimise device-to-server transmissions. The budget learni
Externí odkaz:
http://arxiv.org/abs/2004.06298
Autor:
Kaplan, Müslüm1,2 (AUTHOR) krause-beate@ipfdd.de, Alp, Emre1 (AUTHOR) emrealp@bartin.edu.tr, Krause, Beate2 (AUTHOR), Pötschke, Petra2 (AUTHOR) poe@ipfdd.de
Publikováno v:
Materials (1996-1944). Feb2024, Vol. 17 Issue 4, p774. 15p.