Results 21 to 30 of about 11,928,939 (371)
Active Learning for Domain Adaptation: An Energy-based Approach [PDF]
AAAI Conference on Artificial Intelligence, 2021 Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains. However, there is still enormous potential to be tapped to reach the fully supervised performance. In this paper, we
Binhui Xie +5 more
semanticscholar +1 more source
Active inference and learning [PDF]
Neuroscience & Biobehavioral Reviews, 2016 This paper offers an active inference account of choice behaviour and learning. It focuses on the distinction between goal-directed and habitual behaviour and how they contextualise each other. We show that habits emerge naturally (and autodidactically) from sequential policy optimisation when agents are equipped with state-action policies.
Friston, Karl +5 more
openaire +8 more sources
Optimism in Active Learning [PDF]
Computational Intelligence and Neuroscience, 2015 Active learning is the problem of interactively constructing the training set used in classification in order to reduce its size. It would ideally successively add the instance-label pair that decreases the classification error most. However, the effect of the addition of a pair is not known in advance.
Collet, Timothé, Pietquin, Olivier
openaire +6 more sources
International Journal of Behavioral Nutrition and Physical Activity, 2023 Background Physically active learning (PAL) has emerged as a promising way of eliciting health and education-based outcomes for pupils. Concurrently, research suggests large variability in how PAL is perceived, operationalized, and prioritized in ...
Anna Chalkley +4 more
doaj +1 more source
Sim-to-real via latent prediction: Transferring visual non-prehensile manipulation policies
Frontiers in Robotics and AI, 2023 Reinforcement Learning has been shown to have a great potential for robotics. It demonstrated the capability to solve complex manipulation and locomotion tasks, even by learning end-to-end policies that operate directly on visual input, removing the need
Carlo Rizzardo +3 more
doaj +1 more source
Influence Selection for Active Learning [PDF]
IEEE International Conference on Computer Vision, 2021 The existing active learning methods select the samples by evaluating the sample’s uncertainty or its effect on the diversity of labeled datasets based on different task-specific or model-specific criteria.
Zhuoming Liu +5 more
semanticscholar +1 more source
Scientific Reports, 2022 The aim of our systematic review and meta-analysis was to quantitatively synthesise the effects of school-based peer-led interventions on leaders’ academic, psychosocial, behavioural, and physical outcomes. Eligible studies were those that: (i) evaluated
Levi Wade +9 more
doaj +1 more source
Cold-start Active Learning through Self-Supervised Language Modeling [PDF]
Conference on Empirical Methods in Natural Language Processing, 2020 Active learning strives to reduce annotation costs by choosing the most critical examples to label. Typically, the active learning strategy is contingent on the classification model.
Michelle Yuan +2 more
semanticscholar +1 more source
Active Learning for Deep Visual Tracking [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2021 Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years. Generally, training a deep CNN model requires numerous labeled training samples, and the number and quality of these samples directly ...
Di Yuan +4 more
semanticscholar +1 more source
Septentrio Conference Series, 2020 First year architecture students are introduced to the library by taking part in an “Escape Room” activity in the KTH library. The aim of this initiative is to introduce the students to the library space and the library's resources in an interactive and playful way and to enable them to learn and reflect upon their learning within the frame of an ...
Lenita Brodin Berggren, Ika Jorum
openaire +4 more sources