Zobrazeno 1 - 10
of 876
pro vyhledávání: '"Davidson, Ian A"'
Autor:
Livanos, Michael, Davidson, Ian
Deep anomaly detection (AD) is perhaps the most controversial of data analytic tasks as it identifies entities that are then specifically targeted for further investigation or exclusion. Also controversial is the application of AI to facial imaging d
Externí odkaz:
http://arxiv.org/abs/2407.19646
In this study, we examine the efficacy of post-hoc local attribution methods in identifying features with predictive power from irrelevant ones in domains characterized by a low signal-to-noise ratio (SNR), a common scenario in real-world machine lea
Externí odkaz:
http://arxiv.org/abs/2406.12150
Autor:
Livanos, Michael, Davidson, Ian
Deep learning is extensively used in many areas of data mining as a black-box method with impressive results. However, understanding the core mechanism of how deep learning makes predictions is a relatively understudied problem. Here we explore the n
Externí odkaz:
http://arxiv.org/abs/2403.18278
Autor:
Zaiko, Anastasija, Cardeccia, Alice, Carlton, James T., Clark, Graeme F., Creed, Joel C., Davidson, Ian, Floerl, Oliver, Galil, Bella, Grosholz, Edwin, Hopkins, Grant A., Johnston, Emma L., Kotta, Jonne, Marchini, Agnese, Ojaveer, Henn, Ruiz, Gregory, Therriault, Thomas W., Inglis, Graeme J.
Publikováno v:
Diversity and Distributions, 2024 Jul 01. 30(7), 1-22.
Externí odkaz:
https://www.jstor.org/stable/48777292
Knowledge distillation is a simple but powerful way to transfer knowledge between a teacher model to a student model. Existing work suffers from at least one of the following key limitations in terms of direction and scope of transfer which restrict
Externí odkaz:
http://arxiv.org/abs/2402.05942
Autor:
Szwaj, Marzanna, Davidson, Ian A, Johnson, Peter B, Jasion, Greg, Jung, Yongmin, Sandoghchi, Seyed Reza, Herdzik, Krzysztof P, Bourdakos, Konstantinos N, Wheeler, Natalie V, Mulvad, Hans Christian, Richardson, David J, Poletti, Francesco, Mahajan, Sumeet
In this work, we study a new hollow-core (air-filled) double-clad anti-resonant fiber (DC-ARF) as a potent candidate for multiphoton micro-endoscopy. We compare the fiber characteristics with a single-clad anti-resonant fiber (SC-ARF) and a solid cor
Externí odkaz:
http://arxiv.org/abs/2311.03214
Autor:
Ji, Kunhao, Davidson, Ian, Sahu, Jayantha, Richardson, David. J., Wabnitz, Stefan, Guasoni, Massimiliano
Novel fundamental notions helping in the interpretation of the complex dynamics of nonlinear systems are essential to our understanding and ability to exploit them. In this work we predict and demonstrate experimentally a fundamental property of Kerr
Externí odkaz:
http://arxiv.org/abs/2310.13875
Autor:
Lekosiotis, Athanasios, Belli, Federico, Brahms, Christian, Sabbah, Mohammed, Sakr, Hesham, Davidson, Ian A., Poletti, Francesco, Travers, John C.
We report the flexible on-target delivery of 800 nm wavelength, 5 GW peak power, 40 fs duration laser pulses through an evacuated and tightly coiled 10 m long hollow-core nested anti-resonant fiber by positively chirping the input pulses to compensat
Externí odkaz:
http://arxiv.org/abs/2305.16911
Publikováno v:
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:6613-6629, 2023
There are synergies of research interests and industrial efforts in modeling fairness and correcting algorithmic bias in machine learning. In this paper, we present a scalable algorithm for spectral clustering (SC) with group fairness constraints. Gr
Externí odkaz:
http://arxiv.org/abs/2210.16435
Autor:
Davidson, Ian, Ravi, S. S.
Existing work on fairness typically focuses on making known machine learning algorithms fairer. Fair variants of classification, clustering, outlier detection and other styles of algorithms exist. However, an understudied area is the topic of auditin
Externí odkaz:
http://arxiv.org/abs/2209.11762