Zobrazeno 1 - 10
of 4 421
pro vyhledávání: '"Rudin, P"'
We present ProtoViT, a method for interpretable image classification combining deep learning and case-based reasoning. This method classifies an image by comparing it to a set of learned prototypes, providing explanations of the form ``this looks lik
Externí odkaz:
http://arxiv.org/abs/2410.20722
Sparsity is a central aspect of interpretability in machine learning. Typically, sparsity is measured in terms of the size of a model globally, such as the number of variables it uses. However, this notion of sparsity is not particularly relevant for
Externí odkaz:
http://arxiv.org/abs/2410.20483
Survival analysis is an important research topic with applications in healthcare, business, and manufacturing. One essential tool in this area is the Cox proportional hazards (CPH) model, which is widely used for its interpretability, flexibility, an
Externí odkaz:
http://arxiv.org/abs/2410.19081
Autor:
Bastawrous, Mary V., Chen, Zhi, Ogren, Alexander C., Daraio, Chiara, Rudin, Cynthia, Brinson, L. Catherine
Manipulating the dispersive characteristics of vibrational waves is beneficial for many applications, e.g., high-precision instruments. architected hierarchical phononic materials have sparked promise tunability of elastodynamic waves and vibrations
Externí odkaz:
http://arxiv.org/abs/2408.08428
Schenkerian Analysis (SchA) is a uniquely expressive method of music analysis, combining elements of melody, harmony, counterpoint, and form to describe the hierarchical structure supporting a work of music. However, despite its powerful analytical u
Externí odkaz:
http://arxiv.org/abs/2408.07184
Autor:
Cook, Matthew S., Arellano, David C., Prada, Derek V., Rudin, Sven P., Bauer, Eric D., Phelan, W. Adam
We present the ab initio supported discovery of two new Pu based intermetallic compounds, PuNiSn and PuPtSn. Using density functional theory, the formation energies within the relevant ternary phase diagrams were calculated to predict the stability o
Externí odkaz:
http://arxiv.org/abs/2407.19581
We show that interactions between axion-like particles (ALPs) and co-dimension one defects, such as phase-transition bubble walls and solitonic domain walls, can lead to important changes in the evolution of both walls and ALPs. The leading effect ar
Externí odkaz:
http://arxiv.org/abs/2407.09603
Autor:
Rudin, Cynthia, Zhong, Chudi, Semenova, Lesia, Seltzer, Margo, Parr, Ronald, Liu, Jiachang, Katta, Srikar, Donnelly, Jon, Chen, Harry, Boner, Zachery
Publikováno v:
ICML (spotlight), 2024
The Rashomon Effect, coined by Leo Breiman, describes the phenomenon that there exist many equally good predictive models for the same dataset. This phenomenon happens for many real datasets and when it does, it sparks both magic and consternation, b
Externí odkaz:
http://arxiv.org/abs/2407.04846
Autor:
Willard, Frank, Moffett, Luke, Mokel, Emmanuel, Donnelly, Jon, Guo, Stark, Yang, Julia, Kim, Giyoung, Barnett, Alina Jade, Rudin, Cynthia
Prototypical-part models are a popular interpretable alternative to black-box deep learning models for computer vision. However, they are difficult to train, with high sensitivity to hyperparameter tuning, inhibiting their application to new datasets
Externí odkaz:
http://arxiv.org/abs/2406.14675
Autor:
Yang, Julia, Barnett, Alina Jade, Donnelly, Jon, Kishore, Satvik, Fang, Jerry, Schwartz, Fides Regina, Chen, Chaofan, Lo, Joseph Y., Rudin, Cynthia
Digital mammography is essential to breast cancer detection, and deep learning offers promising tools for faster and more accurate mammogram analysis. In radiology and other high-stakes environments, uninterpretable ("black box") deep learning models
Externí odkaz:
http://arxiv.org/abs/2406.06386