Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Jwala Dhamala"'
Autor:
Md Shakil Zaman, Jwala Dhamala, Pradeep Bajracharya, John L. Sapp, B. Milan Horácek, Katherine C. Wu, Natalia A. Trayanova, Linwei Wang
Publikováno v:
Frontiers in Physiology, Vol 12 (2021)
Probabilistic estimation of cardiac electrophysiological model parameters serves an important step toward model personalization and uncertain quantification. The expensive computation associated with these model simulations, however, makes direct Mar
Externí odkaz:
https://doaj.org/article/313fbb84f66147dc8ced07c71a39bf14
Autor:
Rahul Gupta, Lisa Bauer, Kai-Wei Chang, Jwala Dhamala, Aram Galstyan, Palash Goyal, Qian Hu, Avni Khatri, Rohit Parimi, Charith Peris, Apurv Verma, Richard Zemel, Prem Natarajan
Publikováno v:
Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::30ef11cb8cbdca80359d4f69f4cc8521
https://doi.org/10.1145/3539597.3575785
https://doi.org/10.1145/3539597.3575785
Autor:
Yang Cao, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta, Varun Kumar, Jwala Dhamala, Aram Galstyan
Multiple metrics have been introduced to measure fairness in various natural language processing tasks. These metrics can be roughly categorized into two categories: 1) \emph{extrinsic metrics} for evaluating fairness in downstream applications and 2
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3467ba85c4dbc7d917e39f1bac180dc7
http://arxiv.org/abs/2203.13928
http://arxiv.org/abs/2203.13928
Several prior works have shown that language models (LMs) can generate text containing harmful social biases and stereotypes. While decoding algorithms play a central role in determining properties of LM generated text, their impact on the fairness o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8aee20cb7463927dd6b4fd32cfe85d37
Autor:
Linwei Wang, Shakil Zaman, Katherine C. Wu, Pradeep Bajracharya, Natalia A. Trayanova, B. Milan Horacek, Jwala Dhamala, John L. Sapp
Publikováno v:
Frontiers in Physiology, Vol 12 (2021)
Probabilistic estimation of cardiac electrophysiological model parameters serves an important step toward model personalization and uncertain quantification. The expensive computation associated with these model simulations, however, makes direct Mar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::455584b52fdc67d9467f22a7dff216d9
https://doi.org/10.3389/fphys.2021.740306
https://doi.org/10.3389/fphys.2021.740306
Publikováno v:
KDD
The use of machine learning (ML) based systems has become ubiquitous including their usage in critical applications like medicine and assistive technologies. Therefore, it is important to determine the trustworthiness of these ML models and tasks. A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7dec1a137560410e2028b3a454a3081
https://doi.org/10.1145/3447548.3469458
https://doi.org/10.1145/3447548.3469458
Publikováno v:
ACL/IJCNLP (Findings)
Existing bias mitigation methods to reduce disparities in model outcomes across cohorts have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training. Separately, certified word substi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d5436f52f1420365d6d542e5bd8f25d3
http://arxiv.org/abs/2106.10826
http://arxiv.org/abs/2106.10826
Autor:
Satyapriya Krishna, Jwala Dhamala, Tony Sun, Varun Kumar, Rahul Gupta, Kai-Wei Chang, Yada Pruksachatkun
Publikováno v:
FAccT
Recent advances in deep learning techniques have enabled machines to generate cohesive open-ended text when prompted with a sequence of words as context. While these models now empower many downstream applications from conversation bots to automatic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c9c887a4cd9f5a38fe4317540b6c3ad
https://doi.org/10.1145/3442188.3445924
https://doi.org/10.1145/3442188.3445924
Autor:
Anoop Kumar, Jwala Dhamala, Rahul Gupta, Sriram Venkatapathy, Ansel MacLaughlin, Ragav Venkatesan
Publikováno v:
Insights
Neural Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-art (SOTA) performance on variety of natural language processing and c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c59abd5f64e361c0401cd0b10c7ae1cd
Autor:
Natalia A. Trayanova, B. Milan Horacek, Katherine C. Wu, Hermenegild Arevalo, John L. Sapp, Jwala Dhamala, Linwei Wang
Publikováno v:
Medical Image Analysis. 48:43-57
Model personalization requires the estimation of patient-specific tissue properties in the form of model parameters from indirect and sparse measurement data. Moreover, a low-dimensional representation of the parameter space is needed, which often ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d2a989f92321311a7fb216185216b8a
https://doi.org/10.1016/j.media.2018.05.007
https://doi.org/10.1016/j.media.2018.05.007