Results 11 to 20 of about 11,928,939 (371)
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.
Donggeun Yoo, In-So Kweon
semanticscholar +5 more sources
USING ACTIVE LEARNING IN HYBRID LEARNING ENVIRONMENTS [PDF]
EPJ Web of Conferences, 2021 In this paper, an innovative pedagogical approach relying on flipped classroom and offered in a hybrid learning environment combining on-site and off-site attendees is proposed.
Demazière C
doaj +7 more sources
Reinforcement learning or active inference? [PDF]
PLoS ONE, 2009 This paper questions the need for reinforcement learning or control theory when optimising behaviour. We show that it is fairly simple to teach an agent complicated and adaptive behaviours using a free-energy formulation of perception.
A Gillies +64 more
core +14 more sources
Learning Active Learning from Data [PDF]
, 2017 In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state.
Fua, Pascal +2 more
core +4 more sources
Learning to Sample: an Active Learning Framework [PDF]
arXiv, 2019 Meta-learning algorithms for active learning are emerging as a promising paradigm for learning the ``best'' active learning strategy. However, current learning-based active learning approaches still require sufficient training data so as to generalize meta-learning models for active learning.
Qing Wang, Fangbing Liu, Jingyu Shao
arxiv +5 more sources
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 ...
Jian Sun +3 more
openaire +3 more sources
24-hour movement behaviours and self-rated health in Chinese adolescents: a questionnaire-based survey in Eastern China [PDF]
PeerJ, 2023 Objective Although much evidence has demonstrated the benefits of adhering to the 24-hour movement guidelines, little is known about their association with self-rated health in adolescents.
Guanghui Shi +6 more
doaj +2 more sources
The MLIP package: moment tensor potentials with MPI and active learning [PDF]
Machine Learning: Science and Technology, 2020 The subject of this paper is the technology (the ‘how’) of constructing machine-learning interatomic potentials, rather than science (the ‘what’ and ‘why’) of atomistic simulations using machine-learning potentials. Namely, we illustrate how to construct
I. Novikov +3 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 +4 more sources
Multiple Instance Active Learning for Object Detection [PDF]
Computer Vision and Pattern Recognition, 2021 Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection.
Tianning Yuan +6 more
semanticscholar +1 more source