Zobrazeno 1 - 10
of 6 209
pro vyhledávání: '"Covert, A."'
Recent works have shown that machine learning models improve at a predictable rate with the total amount of training data, leading to scaling laws that describe the relationship between error and dataset size. These scaling laws can help design a mod
Externí odkaz:
http://arxiv.org/abs/2405.20456
Many tasks in explainable machine learning, such as data valuation and feature attribution, perform expensive computation for each data point and can be intractable for large datasets. These methods require efficient approximations, and learning a ne
Externí odkaz:
http://arxiv.org/abs/2401.15866
Contrastive analysis (CA) refers to the exploration of variations uniquely enriched in a target dataset as compared to a corresponding background dataset generated from sources of variation that are irrelevant to a given task. For example, a biomedic
Externí odkaz:
http://arxiv.org/abs/2310.18531
Autor:
COVERT, BRYCE (AUTHOR)
Publikováno v:
Nation. Apr2024, Vol. 318 Issue 4, p22-29. 8p. 6 Color Photographs, 1 Cartoon or Caricature.
To explain predictions made by complex machine learning models, many feature attribution methods have been developed that assign importance scores to input features. Some recent work challenges the robustness of these methods by showing that they are
Externí odkaz:
http://arxiv.org/abs/2306.07462
Dynamic feature selection, where we sequentially query features to make accurate predictions with a minimal budget, is a promising paradigm to reduce feature acquisition costs and provide transparency into a model's predictions. The problem is challe
Externí odkaz:
http://arxiv.org/abs/2306.03301
Feature selection helps reduce data acquisition costs in ML, but the standard approach is to train models with static feature subsets. Here, we consider the dynamic feature selection (DFS) problem where a model sequentially queries features based on
Externí odkaz:
http://arxiv.org/abs/2301.00557
Publikováno v:
Scientific Data, Vol 11, Iss 1, Pp 1-12 (2024)
Abstract The concentration of chlorophyll a in phytoplankton and periphyton represents the amount of algal biomass. We compiled an 18-year record (2005–2022) of pigment data from water bodies across the United States (US) to support efforts to deve
Externí odkaz:
https://doaj.org/article/895fa1c5464446ba997e4d505adbb88c
Autor:
Covert, Bryce (AUTHOR)
Publikováno v:
Nation. 12/25/2023, Vol. 317 Issue 13, p36-41. 6p. 3 Color Photographs, 1 Black and White Photograph, 1 Cartoon or Caricature.
Open-vocabulary models are a promising new paradigm for image classification. Unlike traditional classification models, open-vocabulary models classify among any arbitrary set of categories specified with natural language during inference. This natur
Externí odkaz:
http://arxiv.org/abs/2209.03320