Zobrazeno 1 - 10
of 1 248
pro vyhledávání: '"Earls P"'
Large language models (LLMs) demonstrate remarkable emergent abilities to perform in-context learning across various tasks, including time series forecasting. This work investigates LLMs' ability to estimate probability density functions (PDFs) from
Externí odkaz:
http://arxiv.org/abs/2410.05218
Large Language Models achieve next-token prediction by transporting a vectorized piece of text (prompt) across an accompanying embedding space under the action of successive transformer layers. The resulting high-dimensional trajectories realize diff
Externí odkaz:
http://arxiv.org/abs/2410.01545
Pretrained large language models (LLMs) are surprisingly effective at performing zero-shot tasks, including time-series forecasting. However, understanding the mechanisms behind such capabilities remains highly challenging due to the complexity of th
Externí odkaz:
http://arxiv.org/abs/2402.00795
Autor:
Stephany, Robert, Earls, Christopher
We introduce Weak-PDE-LEARN, a Partial Differential Equation (PDE) discovery algorithm that can identify non-linear PDEs from noisy, limited measurements of their solutions. Weak-PDE-LEARN uses an adaptive loss function based on weak forms to train a
Externí odkaz:
http://arxiv.org/abs/2309.04699
Autor:
Howard L McLeod, A Dimitrios Colevas, Georges Azzi, Kevin C Flanagan, Douglas Adkins, Jessica Ley, Ezra E W Cohen, James Wade, Jon Earls, Jeffrey Hiken, Rachel L Wellinghoff, Michelle M Ponder, William H Westra, Vera Vavinskaya, Leisa Sutton, Ida Deichaite, Orlan K Macdonald, Karim Welaya, Andrew W Pippas, Jennifer Slim, Bruce Bank, Xingwei Sui, Steven E Kossman, Todd D Shenkenberg, Warren L Alexander, Katharine A Price, David N Messina, Jarret I Glasscock, Eric J Duncavage
Publikováno v:
Journal for ImmunoTherapy of Cancer, Vol 12, Iss 11 (2024)
Background Despite advances in cancer care and detection, >65% of patients with squamous cell cancer of the head and neck (HNSCC) will develop recurrent and/or metastatic disease. The prognosis for these patients is poor with a 5-year overall surviva
Externí odkaz:
https://doaj.org/article/5aeea84f23854b819fffb4fd1e4886a8
Autor:
Stephany, Robert, Earls, Christopher
In this paper, we introduce PDE-LEARN, a novel deep learning algorithm that can identify governing partial differential equations (PDEs) directly from noisy, limited measurements of a physical system of interest. PDE-LEARN uses a Rational Neural Netw
Externí odkaz:
http://arxiv.org/abs/2212.04971
We present a data-driven approach to mathematically model physical systems whose governing partial differential equations are unknown, by learning their associated Green's function. The subject systems are observed by collecting input-output pairs of
Externí odkaz:
http://arxiv.org/abs/2211.06299
The Effect of A Flywheel Hip Extension Vs A Traditional Hip Extension Exercise on Hamstring Strength
Publikováno v:
International Journal of Strength and Conditioning, Vol 4, Iss 1 (2024)
The main aim of this present study was to compare the effect of a flywheel hip extension exercise versus a traditional gravity-dependent exercise on hamstring strength. Twenty U-20 male soccer players volunteered to participate in the study. None had
Externí odkaz:
https://doaj.org/article/e16380f12a3e4570a101c5731d95419a
Autor:
Stephany, Robert, Earls, Christopher
PDE discovery shows promise for uncovering predictive models of complex physical systems but has difficulty when measurements are sparse and noisy. We introduce a new approach for PDE discovery that uses two Rational Neural Networks and a principled
Externí odkaz:
http://arxiv.org/abs/2111.00998
Scientific machine learning has been successfully applied to inverse problems and PDE discovery in computational physics. One caveat concerning current methods is the need for large amounts of ("clean") data, in order to characterize the full system
Externí odkaz:
http://arxiv.org/abs/2108.04085