Zobrazeno 1 - 10
of 21 979
pro vyhledávání: '"Som A"'
In large deep neural networks that seem to perform surprisingly well on many tasks, we also observe a few failures related to accuracy, social biases, and alignment with human values, among others. Therefore, before deploying these models, it is cruc
Externí odkaz:
http://arxiv.org/abs/2410.16738
Autor:
Sagar, Som, Taparia, Aditya, Mankodiya, Harsh, Bidare, Pranav, Zhou, Yifan, Senanayake, Ransalu
Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies, lack insights
Externí odkaz:
http://arxiv.org/abs/2409.10733
Concept-based explanations have become a popular choice for explaining deep neural networks post-hoc because, unlike most other explainable AI techniques, they can be used to test high-level visual "concepts" that are not directly related to feature
Externí odkaz:
http://arxiv.org/abs/2408.13438
High dimensional quantum entanglement and the advancements in their experimental realization provide a playground for fundamental research and eventually lead to quantum technological developments. The Horodecki criterion determines whether a state v
Externí odkaz:
http://arxiv.org/abs/2408.10350
Autor:
Nath, Utkarsh, Goel, Rajeev, Jeon, Eun Som, Kim, Changhoon, Min, Kyle, Yang, Yezhou, Yang, Yingzhen, Turaga, Pavan
To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines. However, the diffusion models used in these techniques a
Externí odkaz:
http://arxiv.org/abs/2408.05938
Various generalizations of the scalar, axisymmetric Aretakis "horizon hair" for extremal black holes have recently appeared in the literature. In this paper, we present an expression for a non-axisymmetric Aretakis gravitational charge and its potent
Externí odkaz:
http://arxiv.org/abs/2407.06926
Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing effective information to improve performance is very difficult. To this
Externí odkaz:
http://arxiv.org/abs/2407.05316
Autor:
Jeon, Eun Som, Choi, Hongjun, Shukla, Ankita, Wang, Yuan, Lee, Hyunglae, Buman, Matthew P., Turaga, Pavan
Publikováno v:
Engineering Applications of Artificial Intelligence, 130, 107719 (2024)
Deep learning methods have achieved a lot of success in various applications involving converting wearable sensor data to actionable health insights. A common application areas is activity recognition, where deep-learning methods still suffer from li
Externí odkaz:
http://arxiv.org/abs/2407.05315
In large deep neural networks that seem to perform surprisingly well on many tasks, we also observe a few failures related to accuracy, social biases, and alignment with human values, among others. Therefore, before deploying these models, it is cruc
Externí odkaz:
http://arxiv.org/abs/2406.07145
Autor:
Hong, Jinyung, Jeon, Eun Som, Kim, Changhoon, Park, Keun Hee, Nath, Utkarsh, Yang, Yezhou, Turaga, Pavan, Pavlic, Theodore P.
Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD) generalization. Althoug
Externí odkaz:
http://arxiv.org/abs/2403.14140