Zobrazeno 1 - 9
of 9
pro vyhledávání: '"N. Mert Vural"'
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems
IEEE Transactions on Neural Networks and Learning Systems.
IEEE Transactions on Neural Networks and Learning Systems.
Recurrent Neural Networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies. As an RNN model, Long-Short-Term-Memory Networks (LSTMs) are commonly preferred in practice, as these networks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8a97dfc5313576cd032b515110561c2
https://hdl.handle.net/11693/77682
https://hdl.handle.net/11693/77682
Publikováno v:
SIU
In this paper, we study the online shortest path learning problem under semi-bandit feedback in adversarial and non-stationary environments. To develop an efficient algorithm, we use the online convex optimization framework. We introduce an optimal o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::851b5f06f0df29f2681db8c492beb4b0
https://doi.org/10.1109/siu49456.2020.9302496
https://doi.org/10.1109/siu49456.2020.9302496
Publikováno v:
SIU
In this paper, we study the online shortest path learning problem under semi-bandit feedback in adversarial environments. To this end, we use the online convex optimization framework. We introduce an optimal online shortest path algorithm that guaran
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e908f9f48089cfc5fda138611485d3bb
https://doi.org/10.1109/siu49456.2020.9302479
https://doi.org/10.1109/siu49456.2020.9302479
Publikováno v:
SIU
In this study, we work on online learning with long short term memory (LSTM) based networks is investigated. For LSTM-based online learning, a computationally efficient training algorithm based on extended Kalman filter (EKF) is proposed. We show t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::217b2ff884e4f8dad290cf413f034cdb
https://doi.org/10.1109/siu49456.2020.9302071
https://doi.org/10.1109/siu49456.2020.9302071
Publikováno v:
2020 28th Signal Processing and Communications Applications Conference (SIU).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09ea9c9e4bbbaf5d00e46433f2d38b67
https://doi.org/10.1109/siu49456.2020.9302388
https://doi.org/10.1109/siu49456.2020.9302388
Publikováno v:
2020 28th Signal Processing and Communications Applications Conference (SIU).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d1459908f5421fafc580c87720a0524
https://doi.org/10.1109/siu49456.2020.9302395
https://doi.org/10.1109/siu49456.2020.9302395
Publikováno v:
IEEE Transactions on Signal Processing
We study adaptive (or online) nonlinear regression with Long-Short-Term-Memory (LSTM) based networks, i.e., LSTM-based adaptive learning. In this context, we introduce an efficient Extended Kalman filter (EKF) based second-order training algorithm. O
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::deab45265e3adf21bf9937bea8bc5adf
http://arxiv.org/abs/1910.09857
http://arxiv.org/abs/1910.09857
Publikováno v:
Proceedings Optical Diagnostics and Sensing XIX: Toward Point-of-Care Diagnostics
Date of Conference: 2-7 February 2019 Conference name: SPIE BIOS, 2019 Non-invasive blood glucose measurement has long been desired since the invasive methods are not suitable to perform continuous monitoring. Near Infrared Spectroscopy is one of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::00c38b7fc864d02d2bb0e6313c4eeb78
https://hdl.handle.net/11693/52931
https://hdl.handle.net/11693/52931