Zobrazeno 1 - 10
of 1 375
pro vyhledávání: '"Ahle A"'
Autor:
Klett, Phoebe, Ahle, Thomas
Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al., 2022), that giv
Externí odkaz:
http://arxiv.org/abs/2406.02332
In complex and unknown processes, global models are initially generated over the entire experimental space, but they often fail to provide accurate predictions in local areas. Recognizing this limitation, this study addresses the need for models that
Externí odkaz:
http://arxiv.org/abs/2405.01052
Autor:
Aifer, Maxwell, Melanson, Denis, Donatella, Kaelan, Crooks, Gavin, Ahle, Thomas, Coles, Patrick J.
While physics-based computing can offer speed and energy efficiency compared to digital computing, it also is subject to errors that must be mitigated. For example, many error mitigation methods have been proposed for quantum computing. However this
Externí odkaz:
http://arxiv.org/abs/2401.16231
Autor:
Melanson, Denis, Khater, Mohammad Abu, Aifer, Maxwell, Donatella, Kaelan, Gordon, Max Hunter, Ahle, Thomas, Crooks, Gavin, Martinez, Antonio J., Sbahi, Faris, Coles, Patrick J.
Recent breakthroughs in artificial intelligence (AI) algorithms have highlighted the need for novel computing hardware in order to truly unlock the potential for AI. Physics-based hardware, such as thermodynamic computing, has the potential to provid
Externí odkaz:
http://arxiv.org/abs/2312.04836
Bayesian Neural Networks (BNN) have emerged as a crucial approach for interpreting ML predictions. By sampling from the posterior distribution, data scientists may estimate the uncertainty of an inference. Unfortunately many inference samples are oft
Externí odkaz:
http://arxiv.org/abs/2311.13036
Thermodynamic computing exploits fluctuations and dissipation in physical systems to efficiently solve various mathematical problems. For example, it was recently shown that certain linear algebra problems can be solved thermodynamically, leading to
Externí odkaz:
http://arxiv.org/abs/2311.12759
Autor:
Aifer, Maxwell, Donatella, Kaelan, Gordon, Max Hunter, Duffield, Samuel, Ahle, Thomas, Simpson, Daniel, Crooks, Gavin E., Coles, Patrick J.
Linear algebraic primitives are at the core of many modern algorithms in engineering, science, and machine learning. Hence, accelerating these primitives with novel computing hardware would have tremendous economic impact. Quantum computing has been
Externí odkaz:
http://arxiv.org/abs/2308.05660
Embedding tables are used by machine learning systems to work with categorical features. In modern Recommendation Systems, these tables can be very large, necessitating the development of new methods for fitting them in memory, even during training.
Externí odkaz:
http://arxiv.org/abs/2210.05974
Autor:
Ahle, Thomas D.
We prove the inequality $E[(X/\mu)^k] \le (\frac{k/\mu}{\log(k/\mu+1)})^k \le \exp(k^2/(2\mu))$ for sub-Poissonian random variables, such as Binomially or Poisson distributed random variables with mean $\mu$. The asymptotics $1+O(k^2/\mu)$ can be sho
Externí odkaz:
http://arxiv.org/abs/2103.17027
Autor:
Sarah J. Ullrich, Nicholas K. Yung, Tory J. Bauer-Pisani, Nathan L. Maassel, Mary Elizabeth Guerra, Mollie Freedman-Weiss, Samantha L. Ahle, Adele S. Ricciardi, Maor Sauler, W. Mark Saltzman, Alexandra S. Piotrowski-Daspit, David H. Stitelman
Publikováno v:
Molecular Therapy: Nucleic Acids, Vol 32, Iss , Pp 594-602 (2023)
Structural fetal diseases, such as congenital diaphragmatic hernia (CDH) can be diagnosed prenatally. Neonates with CDH are healthy in utero as gas exchange is managed by the placenta, but impaired lung function results in critical illness from the t
Externí odkaz:
https://doaj.org/article/ebec66f2af7e477991414a8b96157976
