Zobrazeno 1 - 10
of 1 995
pro vyhledávání: '"Jayaraman J"'
Publikováno v:
IEEE Access, Vol 11, Pp 108356-108364 (2023)
Recent advancements in developing pre-trained models using large-scale datasets have emphasized the importance of robust protocols to adapt them effectively to domain-specific data, especially when the available data is limited. To achieve data-effic
Externí odkaz:
https://doaj.org/article/e56af13db69242bf9b4d9585cf28ac01
Publikováno v:
IEEE Access, Vol 11, Pp 12858-12869 (2023)
Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, geometry-based alignment methods, e.g., Orthogonal Procrustes Alignment (OPA), formed an important cl
Externí odkaz:
https://doaj.org/article/96e4297483e44cfd8cf4c35d8114dd3e
Autor:
Matthew L Olson, Shusen Liu, Jayaraman J Thiagarajan, Bogdan Kustowski, Weng-Keen Wong, Rushil Anirudh
Publikováno v:
Machine Learning: Science and Technology, Vol 5, Iss 2, p 025054 (2024)
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize be
Externí odkaz:
https://doaj.org/article/18fe84efb9f2405495678c53ed8890df
Publikováno v:
Scientific Reports, Vol 12, Iss 1, Pp 1-15 (2022)
Abstract The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI t
Externí odkaz:
https://doaj.org/article/4b559289c0894052b52c6f8552335505
Autor:
Cho, Min Sang, Grabowski, Paul E., Thopalli, Kowshik, Jayram, Thathachar S., Barrow, Michael J., Thiagarajan, Jayaraman J., Anirudh, Rushil, Le, Hai P., Scott, Howard A., Kallman, Joshua B., Stephens, Branson C., Foord, Mark E., Gaffney, Jim A., Bremer, Peer-Timo
The integration of machine learning techniques into Inertial Confinement Fusion (ICF) simulations has emerged as a powerful approach for enhancing computational efficiency. By replacing the costly Non-Local Thermodynamic Equilibrium (NLTE) model with
Externí odkaz:
http://arxiv.org/abs/2411.08789
LLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns. We hypothesize that enriching prompts with domain-specific insights can improve both the qua
Externí odkaz:
http://arxiv.org/abs/2409.03946
Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation. In this work, we propose DECIDER (Debiasing Classifiers to Identify Errors Reliably), a novel approach that leverages
Externí odkaz:
http://arxiv.org/abs/2408.00331
In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We present a surprising finding that, when recovering the original model ac
Externí odkaz:
http://arxiv.org/abs/2407.00356
Autor:
Narayanaswamy, Vivek, Thopalli, Kowshik, Anirudh, Rushil, Mubarka, Yamen, Sakla, Wesam, Thiagarajan, Jayaraman J.
Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extrapolation capabilities. In this paper, we systematically explore anchor
Externí odkaz:
http://arxiv.org/abs/2406.00529
Autor:
Jayaraman J. Thiagarajan, Bindya Venkatesh, Rushil Anirudh, Peer-Timo Bremer, Jim Gaffney, Gemma Anderson, Brian Spears
Publikováno v:
Nature Communications, Vol 11, Iss 1, Pp 1-10 (2020)
The success of machine learning for scientific discovery normally depends on how well the inherent assumptions match the problem in hand. Here, Thiagarajan et al. alleviate this constraint by allowing the change of optimization criterion in a data-dr
Externí odkaz:
https://doaj.org/article/4e1088a77af74dbeb4fcd4fe665cf79c