Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Tamara Alshammari"'
Meta-learning is a powerful learning paradigm in which solving a new task can benefit from similar tasks for faster adaption (few shot learning). Stochastic gradient descent (SGD) based meta learning has emerged as an attractive solution in the few-s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2b5570603da8c6988176ec8c6cc14cb
http://urn.fi/urn:nbn:fi-fe2023040535118
http://urn.fi/urn:nbn:fi-fe2023040535118
Publikováno v:
ICC
This article deals with the problem of distributed machine learning, in which agents update their models based on their local datasets, and aggregate the updated models collaboratively and in a fully decentralized manner. In this paper, we tackle the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::422a988cca4e1d408e6077c57a76e777
Publikováno v:
IEEE Wireless Communications. 20:62-67
Recent years have witnessed tremendous success and popularity of mobile applications and services, resulting in an explosive growth in the number of mobile devices, as well as in the range and types of things these devices can do. People nowadays bec
We propose a credit-based resource allocation technique for dynamic spectrum access that is robust against malicious and selfish behaviors and ensures good overall system fairness performance while also allowing spectrum users to achieve high amounts
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b65783704c6b9ee21ce5c7ed78bade4f
https://hdl.handle.net/10576/36170
https://hdl.handle.net/10576/36170
Publikováno v:
ICC
We propose a credit-based resource allocation technique for wireless systems with dynamic spectrum access (DSA) capability, such as multichannel wireless sensor networks. The proposed technique is robust against selfish and malicious behaviors by ach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::433bfa258d946b4c047c2136aa3270e0
https://hdl.handle.net/10576/4476
https://hdl.handle.net/10576/4476