Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Erdem Koyuncu"'
Autor:
Erdem Koyuncu
Publikováno v:
Entropy, Vol 26, Iss 7, p 543 (2024)
Wireless communication systems and networks are rapidly evolving to meet the increasing demands for higher data rates, better reliability, and connectivity anywhere, anytime [...]
Externí odkaz:
https://doaj.org/article/16fe29b152e54b39bac8ecacc75189f4
Publikováno v:
IEEE Open Journal of the Communications Society, Vol 4, Pp 1263-1273 (2023)
The traditional approach to distributed deep neural network (DNN) inference in edge computing systems is data-distributed inference. In this paradigm, each worker has a pre-trained DNN model. Using the DNN model, the worker processes the data that is
Externí odkaz:
https://doaj.org/article/0a570704f3124114b71e1663b364a3ee
Publikováno v:
GLOBECOM 2022 - 2022 IEEE Global Communications Conference.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79715cd18c4a713b482ddab6fa3cb364
https://doi.org/10.1109/globecom48099.2022.10001480
https://doi.org/10.1109/globecom48099.2022.10001480
Autor:
Erdem Koyuncu
Publikováno v:
IEEE transactions on neural networks and learning systems.
We consider the problem of clustering a dataset through multiple noisy observations of its members. The goal is to obtain a clustering that is as faithful to the clustering of the original dataset as possible. We propose a centroidal approach whose d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::968e10511371d7eae53fa8706f698dcd
https://pubmed.ncbi.nlm.nih.gov/35731771
https://pubmed.ncbi.nlm.nih.gov/35731771
Publikováno v:
LANMAN
We consider a model-distributed learning framework in which layers of a deep learning model is distributed across multiple workers. To achieve consistent gradient updates during the training phase, model-distributed learning requires the storage of m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6bce43729268ad88491e3a1dd32806c
https://doi.org/10.1109/lanman52105.2021.9478829
https://doi.org/10.1109/lanman52105.2021.9478829
Publikováno v:
ICASSP
The traditional approach to distributed deep neural network (DNN) training is data-distributed learning, which partitions and distributes data to workers. This approach, although has good convergence properties, has high communication cost, which put
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89776c11373dc6eb504410cebe533647
https://doi.org/10.1109/icassp39728.2021.9413553
https://doi.org/10.1109/icassp39728.2021.9413553
State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning to achieve good performance with low computational cost. We propose a novel early exit technique, Early Exit Class Means (E$^2$CM),
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2278a7023ad88cecc68affc93bd67533
We consider a family of vector dot products that can be implemented using sign changes and addition operations only. The dot products are energy-efficient as they avoid the multiplication operation entirely. Moreover, the dot products induce the $\el
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::736fb0c28ed1968883e87e134eaf5669
Publikováno v:
PIMRC
We consider multiple unmanned aerial vehicles (UAVs) at a common altitude serving as data collectors to a network of IoT devices. First, using a probabilistic line of sight channel model, the optimal assignment of IoT devices to the UAVs is determine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06fe7dcf5757dce3ffae3034cb16c1cd
https://doi.org/10.1109/pimrc48278.2020.9217125
https://doi.org/10.1109/pimrc48278.2020.9217125
Autor:
Samuele Battaglino, Erdem Koyuncu
Publikováno v:
ICASSP
Conventional principal component analysis (PCA) finds a principal vector that maximizes the sum of second powers of principal components. We consider a generalized PCA that aims at maximizing the sum of an arbitrary convex function of principal compo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0391f1b12fabfa74add6eb38134534fa
https://doi.org/10.1109/icassp40776.2020.9054154
https://doi.org/10.1109/icassp40776.2020.9054154