Results 11 to 20 of about 578,053 (267)
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
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
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
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
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 +2 more sources
Cartography Active Learning [PDF]
Findings of the Association for Computational Linguistics: EMNLP 2021, 2021 We propose Cartography Active Learning (CAL), a novel Active Learning (AL) algorithm that exploits the behavior of the model on individual instances during training as a proxy to find the most informative instances for labeling. CAL is inspired by data maps, which were recently proposed to derive insights into dataset quality (Swayamdipta et al., 2020).
Mike Zhang, Barbara Plank
openaire +3 more sources
Learning User's Confidence for Active Learning [PDF]
IEEE Transactions on Geoscience and Remote Sensing, 2013 In this paper, we study the applicability of active learning in operative scenarios: more particularly, we consider the well-known contradiction between the active learning heuristics, which rank the pixels according to their uncertainty, and the user's confidence in labeling, which is related to both the homogeneity of the pixel context and user's ...
Devis Tuia, Jordi Muñoz-Marí
openaire +4 more sources
Learning to Sample: An Active Learning Framework [PDF]
2019 IEEE International Conference on Data Mining (ICDM), 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.
Jingyu Shao +2 more
openaire +2 more sources
Active Function Learning [PDF]
, 2018 Abstract How do people actively explore to learn about functional relationships, that is, how continuous inputs map onto continuous outputs? We introduce a novel paradigm to investigate information search in continuous, multi-feature function learning scenarios.
Jones, Angela +3 more
openaire +5 more sources
Active learning enabled activity recognition [PDF]
Pervasive and Mobile Computing, 2016 © 2016 IEEE, 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom)
H. M. Sajjad Hossain +2 more
openaire +1 more source