Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Nilaksh Das"'
Publikováno v:
Journal of Data and Information Quality. 14:1-23
Few-shot learning (FSL) aims at learning to generalize from only a small number of labeled examples for a given target task. Most current state-of-the-art FSL methods typically have two limitations. First, they usually require access to a source data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b9212a50c5417c9ec9c74c946d2a896f
https://doi.org/10.1145/3491232
https://doi.org/10.1145/3491232
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250552
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6687550518c6985bb86f4bb551e3a764
https://doi.org/10.1007/978-3-031-25056-9_29
https://doi.org/10.1007/978-3-031-25056-9_29
Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning
Autor:
Nilaksh Das, Polo Chau
Publikováno v:
Interspeech 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20add59b2a9fac6e2653ccf164fc5377
https://doi.org/10.21437/interspeech.2022-11361
https://doi.org/10.21437/interspeech.2022-11361
Autor:
Sivapriya Vellaichamy, Matthew Hull, Zijie J. Wang, Nilaksh Das, ShengYun Peng, Haekyu Park, Duen Horng Polo Chau
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ba1db248d7f6861b4e2384265565433
https://doi.org/10.1109/cvpr52688.2022.02082
https://doi.org/10.1109/cvpr52688.2022.02082
Autor:
Nilaksh Das, Monica Sunkara, Dhanush Bekal, Duen Horng Chau, Sravan Bodapati, Katrin Kirchhoff
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f45d347116ac3fbebefb6a3283e58a2
https://doi.org/10.1109/icassp43922.2022.9746748
https://doi.org/10.1109/icassp43922.2022.9746748
Autor:
Omar Shaikh, Fred Hohman, Duen Horng Chau, Austin P. Wright, Rahul Duggal, Nilaksh Das, Haekyu Park
Publikováno v:
IEEE transactions on visualization and computer graphics. 28(1)
Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are collectively encoded by multiple neurons. We present NeuroCartography, an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1aa1378d6d259b26f84cb56dfbba8285
https://pubmed.ncbi.nlm.nih.gov/34587079
https://pubmed.ncbi.nlm.nih.gov/34587079
Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in pronunciation and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6deedde2adb061438fdebc760cb880fb
http://arxiv.org/abs/2103.05834
http://arxiv.org/abs/2103.05834
Autor:
Zijie J. Wang, Nilaksh Das, Haekyu Park, Omar Shaikh, Minsuk Kahng, Fred Hohman, Robert Turko, Duen Horng Polo Chau
Publikováno v:
IEEE transactions on visualization and computer graphics. 27(2)
Deep learning's great success motivates many practitioners and students to learn about this exciting technology. However, it is often challenging for beginners to take their first step due to the complexity of understanding and applying deep learning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c022c43a4547d75744c5fd5e3f35b391
https://pubmed.ncbi.nlm.nih.gov/33048723
https://pubmed.ncbi.nlm.nih.gov/33048723
Autor:
Zijie J. Wang, Duen Horng Chau, Nilaksh Das, Haekyu Park, Fred Hohman, Robert Firstman, Emily Rogers
Publikováno v:
IEEE VIS (Short Papers)
Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully crafted perturbations on data inputs that can fool a model into making incorrect predictions. Despite significant resear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9eca2a1f923ad71e946148dc16d4f6e
https://doi.org/10.1109/vis47514.2020.00061
https://doi.org/10.1109/vis47514.2020.00061
Publikováno v:
SIGMOD Conference
Generating large labeled training data is becoming the biggest bottleneck in building and deploying supervised machine learning models. Recently, the data programming paradigm has been proposed to reduce the human cost in labeling training data. Howe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6b0076c614c5c28028e69fb87bd5086
https://doi.org/10.1145/3318464.3380592
https://doi.org/10.1145/3318464.3380592