Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Nixon, Jeremy"'
Autor:
Nixon, Jeremy
This paper presents a novel approach to machine learning algorithm design based on information theory, specifically mutual information (MI). We propose a framework for learning and representing functional relationships in data using MI-based features
Externí odkaz:
http://arxiv.org/abs/2409.14235
We describe cases where real recommender systems were modified in the service of various human values such as diversity, fairness, well-being, time well spent, and factual accuracy. From this we identify the current practice of values engineering: th
Externí odkaz:
http://arxiv.org/abs/2107.10939
Autor:
Nado, Zachary, Band, Neil, Collier, Mark, Djolonga, Josip, Dusenberry, Michael W., Farquhar, Sebastian, Feng, Qixuan, Filos, Angelos, Havasi, Marton, Jenatton, Rodolphe, Jerfel, Ghassen, Liu, Jeremiah, Mariet, Zelda, Nixon, Jeremy, Padhy, Shreyas, Ren, Jie, Rudner, Tim G. J., Sbahi, Faris, Wen, Yeming, Wenzel, Florian, Murphy, Kevin, Sculley, D., Lakshminarayanan, Balaji, Snoek, Jasper, Gal, Yarin, Tran, Dustin
High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ability to compare techniques for improving these estimates is therefore
Externí odkaz:
http://arxiv.org/abs/2106.04015
Publikováno v:
Causal Learning for Decision Making (CLDM) ICLR CLDM 2020
Causal models bring many benefits to decision-making systems (or agents) by making them interpretable, sample-efficient, and robust to changes in the input distribution. However, spurious correlations can lead to wrong causal models and predictions.
Externí odkaz:
http://arxiv.org/abs/2002.05217
One promising approach to dealing with datapoints that are outside of the initial training distribution (OOD) is to create new classes that capture similarities in the datapoints previously rejected as uncategorizable. Systems that generate labels ca
Externí odkaz:
http://arxiv.org/abs/2002.03480
Autor:
Dusenberry, Michael W., Tran, Dustin, Choi, Edward, Kemp, Jonas, Nixon, Jeremy, Jerfel, Ghassen, Heller, Katherine, Dai, Andrew M.
In medicine, both ethical and monetary costs of incorrect predictions can be significant, and the complexity of the problems often necessitates increasingly complex models. Recent work has shown that changing just the random seed is enough for otherw
Externí odkaz:
http://arxiv.org/abs/1906.03842
Autor:
Nixon, Jeremy, Dusenberry, Mike, Jerfel, Ghassen, Nguyen, Timothy, Liu, Jeremiah, Zhang, Linchuan, Tran, Dustin
Overconfidence and underconfidence in machine learning classifiers is measured by calibration: the degree to which the probabilities predicted for each class match the accuracy of the classifier on that prediction. How one measures calibration remain
Externí odkaz:
http://arxiv.org/abs/1904.01685
Deep learning has shown that learned functions can dramatically outperform hand-designed functions on perceptual tasks. Analogously, this suggests that learned optimizers may similarly outperform current hand-designed optimizers, especially for speci
Externí odkaz:
http://arxiv.org/abs/1810.10180
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Nixon, Jeremy
Publikováno v:
All Graduate Plan B and other Reports
This exhibition represents an experimental body of work completed for the Caine College of the Arts. It explores the interplay of explicit and implicit functions within semiotics, while simultaneously communicating the college���s messages and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba3902f49e901a5f0399e9e6dbbc6197