Results 31 to 40 of about 11,928,939 (371)
Physica Scripta, 2023 Abstract In this work we discuss the problem of active learning. We present an approach that is based on A-optimal experimental design of ill-posed problems and show how one can optimally label a data set by partially probing it, and use it to train a deep network. We present two approaches that make different assumptions on the data set.
Tue Boesen, Eldad Haber
openaire +2 more sources
Task-Aware Variational Adversarial Active Learning [PDF]
Computer Vision and Pattern Recognition, 2020 Often, labeling large amount of data is challenging due to high labeling cost limiting the application domain of deep learning techniques. Active learning (AL) tackles this by querying the most informative samples to be annotated among unlabeled pool ...
Kwanyoung Kim +3 more
semanticscholar +1 more source
Systematic Reviews, 2023 Background Sport is a subset of physical activity that can be particularly beneficial for short-and-long-term physical and mental health, and social outcomes in adults.
Narelle Eather +3 more
doaj +1 more source
The Curious Construct of Active Learning
Psychological Science in the Public Interest, 2021 The construct of active learning permeates undergraduate education in science, technology, engineering, and mathematics (STEM), but despite its prevalence, the construct means different things to different people, groups, and STEM domains.
D. Lombardi, T. Shipley
semanticscholar +1 more source
Proceedings of the National Academy of Sciences of the United States of America, 2020 Significance Achievement gaps increase income inequality and decrease workplace diversity by contributing to the attrition of underrepresented students from science, technology, engineering, and mathematics (STEM) majors. We collected data on exam scores
Elli J. Theobald +32 more
semanticscholar +1 more source
Eating habits matter for sleep difficulties in children and adolescents: A cross-sectional study
Frontiers in Pediatrics, 2023 BackgroundSleep difficulties are a common sleep-related problem among children and adolescents. However, the association between eating habits and sleep difficulties has not been extensively studied.
Yaping Zhao +5 more
doaj +1 more source
Variational Adversarial Active Learning [PDF]
IEEE International Conference on Computer Vision, 2019 Active learning aims to develop label-efficient algorithms by sampling the most representative queries to be labeled by an oracle. We describe a pool-based semi-supervised active learning algorithm that implicitly learns this sampling mechanism in an ...
Samarth Sinha +2 more
semanticscholar +1 more source
How to measure uncertainty in uncertainty sampling for active learning
Machine-mediated learning, 2021 Various strategies for active learning have been proposed in the machine learning literature. In uncertainty sampling, which is among the most popular approaches, the active learner sequentially queries the label of those instances for which its current ...
Eyke Hüllermeier
semanticscholar +1 more source
Agnostic active learning [PDF]
Proceedings of the 23rd international conference on Machine learning - ICML '06, 2006 AbstractWe state and analyze the first active learning algorithm that finds an ϵ-optimal hypothesis in any hypothesis class, when the underlying distribution has arbitrary forms of noise. The algorithm, A2 (for Agnostic Active), relies only upon the assumption that it has access to a stream of unlabeled examples drawn i.i.d.
Alina Beygelzimer +2 more
openaire +2 more sources
Approaching physically active learning as a multi, inter, and transdisciplinary research field
Frontiers in Sports and Active Living, 2023 In broad terms, physically active learning is a phenomenon that combines health and educational disciplines to integrate physical activity and core educational goals.
Mathias Brekke Mandelid +1 more
doaj +1 more source