Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Urmish Thakker"'
Publikováno v:
IEEE Internet of Things Journal. 9:1-24
Federated learning (FL) is a distributed machine learning strategy that generates a global model by learning from multiple decentralized edge clients. FL enables on-device training, keeping the client’s local data private, and further, updating the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6dd83bb4017a671b0aec3805c9e217fd
https://doi.org/10.1109/jiot.2021.3095077
https://doi.org/10.1109/jiot.2021.3095077
Publikováno v:
Federated and Transfer Learning ISBN: 9783031117473
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17cd6f6001de881e994832ef62b7436d
https://doi.org/10.1007/978-3-031-11748-0_2
https://doi.org/10.1007/978-3-031-11748-0_2
Autor:
Urmish Thakker, Chu Zhou, Matthew Mattina, Jesse Beu, Ganesh Dasika, Dibakar Gope, Igor Fedorov
Publikováno v:
ACM Journal on Emerging Technologies in Computing Systems. 17:1-18
Micro-controllers (MCUs) make up most of the processors in the world with widespread applicability from automobile to medical devices. The Internet of Things promises to enable these resource-constrained MCUs with machine learning algorithms to provi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9f452e7a611f49a4726316a02244f90
https://doi.org/10.1145/3440016
https://doi.org/10.1145/3440016
Publikováno v:
AIChallengeIoT@SenSys
Recent trends have shown that deep learning models have become larger and more accurate at an increased computational cost, making them difficult to deploy for latency-constrained applications. Conditional execution methods address this increase in c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::07cc802effe807d8007c9f7be913f45c
https://doi.org/10.1145/3417313.3429381
https://doi.org/10.1145/3417313.3429381
Publikováno v:
AIChallengeIoT@SenSys
There has been a recent surge in interest in dynamic inference technologies which can reduce the cost of inference, without sacrificing the accuracy of the model. These models are based on the assumption that not all parts of the output feature map (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f9bb0f6c69317ff79bf96f6803f441f8
https://doi.org/10.1145/3417313.3429380
https://doi.org/10.1145/3417313.3429380
Sequence model based NLP applications can be large. Yet, many applications that benefit from them run on small devices with very limited compute and storage capabilities, while still having run-time constraints. As a result, there is a need for a com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb28ec4bdde46a856f6513e7d93cc3ec
Autor:
Ganesh Dasika, Jesse Beu, Matthew Mattina, Chu Zhou, Dibakar Gope, Urmish Thakker, Igor Fedorov
Publikováno v:
EMC2@NeurIPS
Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. Thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2988bbc0be9b2069075430cdd4472245
https://doi.org/10.1109/emc2-nips53020.2019.00012
https://doi.org/10.1109/emc2-nips53020.2019.00012
Publikováno v:
SenSys-ML
Recurrent Neural Networks (RNNs) break a time-series input (or a sentence) into multiple time-steps (or words) and process it one time-step (word) at a time. However, not all of these time-steps (words) need to be processed to determine the final out
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::69884c0ffa6c63dd26199bbbca6890e8
https://doi.org/10.1145/3362743.3362965
https://doi.org/10.1145/3362743.3362965
Publikováno v:
2019 2nd Workshop on Energy Efficient Machine Learning and Cognitive Computing for Embedded Applications (EMC2).
Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints. As a result, there is a need f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b05ec13d20136d062116081ebb758b3f
https://doi.org/10.1109/emc249363.2019.00013
https://doi.org/10.1109/emc249363.2019.00013