Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Som, Anirudh"'
Paraphrasing of offensive content is a better alternative to content removal and helps improve civility in a communication environment. Supervised paraphrasers; however, rely heavily on large quantities of labelled data to help preserve meaning and i
Externí odkaz:
http://arxiv.org/abs/2310.10707
Autor:
Jeon, Eun Som, Som, Anirudh, Shukla, Ankita, Hasanaj, Kristina, Buman, Matthew P., Turaga, Pavan
Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number of parameters makes it difficult to integrate these models into edge de
Externí odkaz:
http://arxiv.org/abs/2201.00111
Autor:
Som, Anirudh, Kim, Sujeong, Lopez-Prado, Bladimir, Dhamija, Svati, Alozie, Nonye, Tamrakar, Amir
Collaboration is identified as a required and necessary skill for students to be successful in the fields of Science, Technology, Engineering and Mathematics (STEM). However, due to growing student population and limited teaching staff it is difficul
Externí odkaz:
http://arxiv.org/abs/2106.09623
Deep neural networks have increasingly been used as an auxiliary tool in healthcare applications, due to their ability to improve performance of several diagnosis tasks. However, these methods are not widely adopted in clinical settings due to the pr
Externí odkaz:
http://arxiv.org/abs/2102.08360
Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks. However, many standard models thus obtained often exhibit issues like feature redundancy, low interpretability, and
Externí odkaz:
http://arxiv.org/abs/2009.10762
Autor:
Som, Anirudh, Kim, Sujeong, Lopez-Prado, Bladimir, Dhamija, Svati, Alozie, Nonye, Tamrakar, Amir
K-12 classrooms consistently integrate collaboration as part of their learning experiences. However, owing to large classroom sizes, teachers do not have the time to properly assess each student and give them feedback. In this paper we propose using
Externí odkaz:
http://arxiv.org/abs/2007.06667
Application and use of deep learning algorithms for different healthcare applications is gaining interest at a steady pace. However, use of such algorithms can prove to be challenging as they require large amounts of training data that capture differ
Externí odkaz:
http://arxiv.org/abs/2005.02589
Deep-learning architectures for classification problems involve the cross-entropy loss sometimes assisted with auxiliary loss functions like center loss, contrastive loss and triplet loss. These auxiliary loss functions facilitate better discriminati
Externí odkaz:
http://arxiv.org/abs/2004.09805
At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper, we propose to use Topological Data Analysis (TDA) together with machi
Externí odkaz:
http://arxiv.org/abs/2004.07384
Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. This is greatly attributed to the robustn
Externí odkaz:
http://arxiv.org/abs/1906.01769