Zobrazeno 1 - 10
of 13
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
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.
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).
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).
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
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
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
Autor:
Duen Horng Chau, Zijie J. Wang, Robert Firstman, Haekyu Park, Emily Rogers, Nilaksh Das, Fred Hohman
Publikováno v:
CHI Extended Abstracts
Deep neural networks (DNNs) are increasingly powering high-stakes applications such as autonomous cars and healthcare; however, DNNs are often treated as "black boxes" in such applications. Recent research has also revealed that DNNs are highly vulne