Results 51 to 60 of about 9,437,008 (290)
Bayesian Active Learning in the Presence of Nuisance Parameters
Proceedings of Machine Learning Research, 2023 In many settings, such as scientific inference, optimization, and transfer learning, the learner has a well-defined objective, which can be treated as estimation of a target parameter, and no intrinsic interest in characterizing the entire data-generating process.
Sloman, Sabina J.; id_orcid 0000-0001-7479-4286 +3 more
openaire +5 more sources
Episode-based active learning with Bayesian neural networks [PDF]
, 2017 We investigate different strategies for active learning with Bayesian deep neural networks. We focus our analysis on scenarios where new, unlabeled data is obtained episodically, such as commonly encountered in mobile robotics applications. An evaluation
Sunderhauf, N. +8 more
core +1 more source
Implementation Science Communications, 2022 Background Incorporating physical movement in the teaching of academic content (active learning) is a promising approach to improve children’s health and academic performance.
Timothy J. Walker +4 more
doaj +1 more source
Uncertainty Assessment-Based Active Learning for Reliable Fire Detection Systems
IEEE Access, 2022 Deep learning technologies, due to their advanced pattern extraction and recognition of high-dimensional data, have been widely adopted into multisensor-based fire detection systems.
Young-Jin Kim, Won-Tae Kim
doaj +1 more source
Deep Bayesian Active Learning with Image Data
CoRR, 2017 Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data.
Gal, Y, Islam, R, Ghahramani, Z
openaire +4 more sources
Deep Bayesian Active Semi-Supervised Learning [PDF]
2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 2018 In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep convolutional neural network with as few known labels as possible.
Matthias Rottmann +2 more
openaire +4 more sources
Synthetic Spatial Foraging With Active Inference in a Geocaching Task
Frontiers in Neuroscience, 2022 Humans are highly proficient in learning about the environments in which they operate. They form flexible spatial representations of their surroundings that can be leveraged with ease during spatial foraging and navigation. To capture these abilities, we
Victorita Neacsu +3 more
doaj +1 more source
Bayesian active learning with pretrained language models [PDF]
CoRR, 2021 Active Learning (AL) is a method to iteratively select data for annotation from a pool of unlabeled data, aiming to achieve better model performance than random selection. Previous AL approaches in Natural Language Processing (NLP) have been limited to either task-specific models that are trained from scratch at each iteration using only the labeled ...
Margatina, K., Barrault, L., Aletras, N.
openaire +2 more sources
Automatic evaluation system for vehicle Adaptive cruise control using Bayesian Active Learning
Nihon Kikai Gakkai ronbunshuAdaptive cruise control (ACC) is one of the critical elements of vehicle performance in the market. To ensure the quality of ACC performance, comprehensive evaluations that control both complex test scenarios that reproduce market driving conditions and ...
Mikoto YAMAMOTO +4 more
doaj +1 more source
Active Machine Learning for Chemical Engineers: A Bright Future Lies Ahead!
Engineering, 2023 By combining machine learning with the design of experiments, thereby achieving so-called active machine learning, more efficient and cheaper research can be conducted.
Yannick Ureel +6 more
doaj +1 more source