Zobrazeno 1 - 10
of 90
pro vyhledávání: '"Lovekesh Vig"'
Publikováno v:
International Journal of Prognostics and Health Management, Vol 10, Iss 4 (2019)
rognostics or Remaining Useful Life (RUL) Estimation from multi-sensor time series data is useful to enable condition-based maintenance and ensure high operational availability of equipment. We propose a novel deep learning based approach for Prognos
Externí odkaz:
https://doaj.org/article/16e810e4d03b4d8b8c6c02f9f228b938
Autor:
Sucheta Chauhan, Lovekesh Vig, Michele De Filippo De Grazia, Maurizio Corbetta, Shandar Ahmad, Marco Zorzi
Publikováno v:
Frontiers in Neuroinformatics, Vol 13 (2019)
Stroke causes behavioral deficits in multiple cognitive domains and there is a growing interest in predicting patient performance from neuroimaging data using machine learning techniques. Here, we investigated a deep learning approach based on convol
Externí odkaz:
https://doaj.org/article/a934634cb9d94cf8b06cc56d69dd8135
Publikováno v:
International Journal of Prognostics and Health Management, Vol 9, Iss 1 (2018)
We consider the problem of estimating the remaining useful life (RUL) of a system or a machine from sensor data. Many approaches for RUL estimation based on sensor data make assumptions about how machines degrade. Additionally, sensor data from machi
Externí odkaz:
https://doaj.org/article/3da47e6e55114cb28967e6ba219f32a7
Publikováno v:
Journal of Robotics, Vol 2011 (2011)
Traditional artificial neural network models of learning suffer from catastrophic interference. They are commonly trained to perform only one specific task, and, when trained on a new task, they forget the original task completely. It has been shown
Externí odkaz:
https://doaj.org/article/8b415a82a4d54c73a8a2979b375664d1
Publikováno v:
Computer Vision – ACCV 2022 Workshops ISBN: 9783031270659
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::29f2fab6fa7dccb30995ed4a9073afa0
https://doi.org/10.1007/978-3-031-27066-6_8
https://doi.org/10.1007/978-3-031-27066-6_8
Deep neural networks (DNN) are prone to miscalibrated predictions, often exhibiting a mismatch between the predicted output and the associated confidence scores. Contemporary model calibration techniques mitigate the problem of overconfident predicti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b3f25e57f3c1c14d455a407a6d8ebb1a
http://arxiv.org/abs/2212.10005
http://arxiv.org/abs/2212.10005
Publikováno v:
Data Science. 4:63-83
Capturing data in the form of networks is becoming an increasingly popular approach for modeling, analyzing and visualising complex phenomena, to understand the important properties of the underlying complex processes. Access to many large-scale netw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e81e2be97cf1d576ee6166cb645d572c
https://doi.org/10.3233/ds-210033
https://doi.org/10.3233/ds-210033
Autor:
Amit Sangroya, Suparshva Jain, Lovekesh Vig, null C. Anantaram, Arijit Ukil, Sundeep Khandelwal
Publikováno v:
The International FLAIRS Conference Proceedings. 35
Deep learning techniques are being used for heart rhythm classification from ECG waveforms. Large networks using end-to-end learning such as convolutional neural networks are not easily interpretable by end-users such as doctors. This is because most
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c44bae15f0f0826f01ec37523c68969
https://doi.org/10.32473/flairs.v35i.130681
https://doi.org/10.32473/flairs.v35i.130681
Existing methods for Table Structure Recognition (TSR) from camera-captured or scanned documents perform poorly on complex tables consisting of nested rows / columns, multi-line texts and missing cell data. This is because current data-driven methods
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95d20dd3ed8a4b2e2797e97a3ba9762b
http://arxiv.org/abs/2203.06873
http://arxiv.org/abs/2203.06873
Autor:
Jyoti Narwariya, Chetan Verma, Pankaj Malhotra, Lovekesh Vig, Easwara Subramanian, Sanjay Bhat
In electricity markets, retailers or brokers want to maximize profits by allocating tariff profiles to end consumers. One of the objectives of such demand response management is to incentivize the consumers to adjust their consumption so that the ove
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aa81649d01b0abebebc44635a4125996
http://arxiv.org/abs/2202.05517
http://arxiv.org/abs/2202.05517