Zobrazeno 1 - 10
of 680
pro vyhledávání: '"Arabshahi P"'
Autor:
Fotouhi, Milad, Bahadori, Mohammad Taha, Feyisetan, Oluwaseyi, Arabshahi, Payman, Heckerman, David
The existing algorithms for identification of neurons responsible for undesired and harmful behaviors do not consider the effects of confounders such as topic of the conversation. In this work, we show that confounders can create spurious correlation
Externí odkaz:
http://arxiv.org/abs/2412.02893
Autor:
Fotouhi, Milad, Bahadori, Mohammad Taha, Feyisetan, Oluwaseyi, Arabshahi, Payman, Heckerman, David
We investigate the use of in-context learning and prompt engineering to estimate the contributions of training data in the outputs of instruction-tuned large language models (LLMs). We propose two novel approaches: (1) a similarity-based approach tha
Externí odkaz:
http://arxiv.org/abs/2408.11852
Severe weather events such as floods, hurricanes, earthquakes, and large wind or ice storms can cause extensive damage to electrical distribution networks, requiring a multi-day restoration effort. Complicating the recovery process is the lack of com
Externí odkaz:
http://arxiv.org/abs/2404.03197
Autor:
Wysoczanski, Artur, Ettehadi, Nabil, Arabshahi, Soroush, Sun, Yifei, Stukovsky, Karen Hinkley, Watson, Karol E., Han, MeiLan K., Michos, Erin D, Comellas, Alejandro P., Hoffman, Eric A., Laine, Andrew F., Barr, R. Graham, Angelini, Elsa D.
Pulmonary emphysema, the progressive, irreversible loss of lung tissue, is conventionally categorized into three subtypes identifiable on pathology and on lung computed tomography (CT) images. Recent work has led to the unsupervised learning of ten s
Externí odkaz:
http://arxiv.org/abs/2403.00257
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-14 (2024)
Abstract This paper presents a novel numerical approach for approximating the solution of the model describing the infection of $$CD4^+T$$ C D 4 + T -cells by the human T-cell lymphotropic virus I (HTLV-I).The proposed method utilizes the operational
Externí odkaz:
https://doaj.org/article/74653b2a542945ada23bc8467ab9550c
Publikováno v:
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11360-11397, 2023
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc. Blackbox models are flexible but difficult to explain, while interpretable models are inherently explainable. Yet, interpretable models require extensiv
Externí odkaz:
http://arxiv.org/abs/2307.05350
We use concept-based interpretable models to mitigate shortcut learning. Existing methods lack interpretability. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each expert explain
Externí odkaz:
http://arxiv.org/abs/2302.10289
Autor:
Singla, Sumedha, Murali, Nihal, Arabshahi, Forough, Triantafyllou, Sofia, Batmanghelich, Kayhan
A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples that lie clos
Externí odkaz:
http://arxiv.org/abs/2210.12196
Publikováno v:
IET Generation, Transmission & Distribution, Vol 18, Iss 9, Pp 1919-1934 (2024)
Abstract A machine learning‐based optimized droop method is suggested here to simultaneously reduce the production cost (PC) and power line losses (PLL) for a class of direct current (DC) microgrids (MGs). Traditionally, a communication‐less tech
Externí odkaz:
https://doaj.org/article/7e835cfba9d24c669475afa75e509a7b
Publikováno v:
Applied Physics Reviews 9, 041403 (2022)
Correlations between electrical and thermal conduction in polymer composites are blurred due to the complex contribution of charge and heat carriers at the nanoscale junctions of filler particles. Conflicting reports on the lack or existence of therm
Externí odkaz:
http://arxiv.org/abs/2209.07635