Results 1 to 10 of about 10,830,582 (300)
Learning Loss for Active Learning [PDF]
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019 The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as uncertain. A variety of recent methods have been proposed to apply active learning to deep networks but most of them ...
Donggeun Yoo, In So Kweon
openaire +4 more sources
The Curious Construct of Active Learning
Psychological Science in the Public Interest: A Journal of the American Psychological Society, 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.
Doug Lombardi +2 more
exaly +2 more sources
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 +2 more
exaly +2 more sources
IEEE Access, 2016 Active learning aims at obtaining high-accuracy models with as a few labeled data as possible, by iteratively and elaborately selecting most valuable data to query labels during the learning process, thereby the cost of labeling data can be reduced. Most
Pengcheng Shen +2 more
doaj +2 more sources
A comprehensive survey on deep active learning in medical image analysis [PDF]
Medical Image Anal., 2023 Deep learning has achieved widespread success in medical image analysis, leading to an increasing demand for large-scale expert-annotated medical image datasets.
Haoran Wang +5 more
semanticscholar +1 more source
Activate or Not: Learning Customized Activation [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not. Interestingly, we find Swish, the recent popular NAS-searched activation, can be interpreted as a smooth approximation to ReLU. Intuitively, in the same way, we approximate the more general Maxout family to our novel ACON family ...
Ningning Ma +3 more
openaire +2 more sources
Active learning for data streams: a survey [PDF]
Machine-mediated learning, 2023 Online active learning is a paradigm in machine learning that aims to select the most informative data points to label from a data stream. The problem of minimizing the cost associated with collecting labeled observations has gained a lot of attention in
Davide Cacciarelli, M. Kulahci
semanticscholar +1 more source
Active Learning by Acquiring Contrastive Examples [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 Common acquisition functions for active learning use either uncertainty or diversity sampling, aiming to select difficult and diverse data points from the pool of unlabeled data, respectively.
Katerina Margatina +3 more
semanticscholar +1 more source
A Survey of Deep Active Learning [PDF]
ACM Computing Surveys, 2020 Active learning (AL) attempts to maximize a model’s performance gain while annotating the fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize a massive number of parameters if the model is
Pengzhen Ren +6 more
semanticscholar +1 more source
Expert Systems with Applications, 2022 Machine learning (ML) is increasingly being used in high-stakes applications impacting society. Therefore, it is of critical importance that ML models do not propagate discrimination. Collecting accurate labeled data in societal applications is challenging and costly.
Hadis Anahideh +2 more
openaire +3 more sources