Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Cansu Sen"'
Autor:
Dongyu Zhang, Cansu Sen, Jidapa Thadajarassiri, Thomas Hartvigsen, Xiangnan Kong, Elke Rundensteiner
Publikováno v:
2021 IEEE International Conference on Big Data (Big Data).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::159a2e37bdc9b80dcc85a38bc3304cd3
https://doi.org/10.1109/bigdata52589.2021.9671444
https://doi.org/10.1109/bigdata52589.2021.9671444
Publikováno v:
IEEE BigData
Publicly available pre-trained word embeddings are rich sources for turning critical high-dimensional representations of huge text data repositories into meaningful compact vectors essential for text mining applications. With many of such pre-trained
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::feb13dd3b3e42cac73e1de327d9c1aec
https://doi.org/10.1109/bigdata50022.2020.9378312
https://doi.org/10.1109/bigdata50022.2020.9378312
Publikováno v:
CIKM
Recurrent Neural Networks (RNNs) are the state-of-the-art approach to sequential learning. However, standard RNNs use the same amount of computation to generate their hidden states at each timestep, regardless of the input data. Recent works have beg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::585f452469f668b95dc48ece5c8a206e
https://doi.org/10.1145/3340531.3412018
https://doi.org/10.1145/3340531.3412018
Publikováno v:
KDD
Early multi-label classification of time series, the assignment of a label set to a time series before the series is entirely observed, is critical for time-sensitive domains such as healthcare. In such cases, waiting too long to classify can render
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3318a2ff574a1507c7f94506d5a6f9e3
https://doi.org/10.1145/3394486.3403191
https://doi.org/10.1145/3394486.3403191
Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words?
Publikováno v:
ACL
Motivated by human attention, computational attention mechanisms have been designed to help neural networks adjust their focus on specific parts of the input data. While attention mechanisms are claimed to achieve interpretability, little is known ab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ab7806e0d3108dda2c5ce82ec7b30304
https://doi.org/10.18653/v1/2020.acl-main.419
https://doi.org/10.18653/v1/2020.acl-main.419
Publikováno v:
HEALTHINF
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad57b1d48fe370c4edd56a72b480f89a
https://doi.org/10.5220/0009157406560663
https://doi.org/10.5220/0009157406560663
Publikováno v:
IEEE BigData
Clinical notes correspond to sequences of reports about patients written over time by health-care professionals. With the availability of massive Electronic Health Record (EHR) datasets composed of such clinical notes, machine learning models on thes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc87b8bd57950ff736cc5666f77e9888
https://doi.org/10.1109/bigdata47090.2019.9006400
https://doi.org/10.1109/bigdata47090.2019.9006400
Publikováno v:
IEEE BigData
In spite of clinical notes in Electronic Health Records (EHR) providing abundant information about patient health, effective modeling of clinical notes remains in its infancy. A patient’s clinical notes correspond to a sequence of free-form texts g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d703c74c1ef0c1532ae66da0e492c0a
https://doi.org/10.1109/bigdata47090.2019.9006403
https://doi.org/10.1109/bigdata47090.2019.9006403
Publikováno v:
ICECS
This paper presents an FPGA implementation of the Real Valued Time Delay Neural Network (RVTDNN) based digital predistortion with a very low resource utilization and high throughput. The implementation exploits efficient utilization of FPGA primitive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef0f5c8d4f7bb8ae7ad0240ad5825d40
https://doi.org/10.1109/icecs46596.2019.8964743
https://doi.org/10.1109/icecs46596.2019.8964743
Publikováno v:
KDD
Early classification of time series is the prediction of the class label of a time series before it is observed in its entirety. In time-sensitive domains where information is collected over time it is worth sacrificing some classification accuracy i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::082855f5d5b4dc6807000964a9c89c80
https://doi.org/10.1145/3292500.3330974
https://doi.org/10.1145/3292500.3330974