Results 51 to 60 of about 11,928,939 (371)
Active Learning for BERT: An Empirical Study
Conference on Empirical Methods in Natural Language Processing, 2020 Real world scenarios present a challenge for text classification, since labels are usually expensive and the data is often characterized by class imbalance. Active Learning (AL) is a ubiquitous paradigm to cope with data scarcity.
L. Ein-Dor +9 more
semanticscholar +1 more source
Using Active Learning and Team Competition to Teach Gas Turbine Cycle Design [PDF]
, 2019 An elective, Analysis and Design of Propulsion Systems, has been a traditional lecture course teaching gas turbine engines from a design perspective.
Van Treuren, Kenneth
core +1 more source
Learning functions actively [PDF]
, 2019 How do people actively learn functional rules, i.e. a mapping of continuous inputs onto a continuous output? We investigate information search behavior in a multiple-featurefunction learning task in which participants either actively select or passively receive observations.
Jones, A. +3 more
openaire +4 more sources
International Journal of Behavioral Nutrition and Physical Activity, 2021 Background Physically active learning (PAL) - integration of movement within delivery of academic content - is a core component of many whole-of-school physical activity approaches. Yet, PAL intervention methods and strategies vary and frequently are not
Andrew Daly-Smith +14 more
doaj +1 more source
Active Learning with Statistical Models [PDF]
, 1995 For many types of machine learning algorithms, one can compute the statistically `optimal' way to select training data. In this paper, we review how optimal data selection techniques have been used with feedforward neural networks.
Cohn, D. A. +2 more
core +9 more sources
On the Robustness of Active Learning [PDF]
EPiC Series in Computing, 2019 Active Learning is concerned with the question of how to identify the most useful samples for a Machine Learning algorithm to be trained with. When applied correctly, it can be a very powerful tool to counteract the immense data requirements of Artificial Neural Networks.
Ori Maoz +5 more
openaire +3 more sources
The link between flipped and active learning: a scoping review
Teaching in Higher Education, 2021 Flipped learning in higher education is becoming increasingly widespread. Although the number of flipped learning articles has increased since 2011, systematic reviews of flipped learning have been criticized for lacking a theoretical framework.
Rita Li, Andreas Lund, A. Nordsteien
semanticscholar +1 more source
State-Relabeling Adversarial Active Learning [PDF]
Computer Vision and Pattern Recognition, 2020 Active learning is to design label-efficient algorithms by sampling the most representative samples to be labeled by an oracle. In this paper, we propose a state relabeling adversarial active learning model (SRAAL), that leverages both the annotation and
Beichen Zhang +5 more
semanticscholar +1 more source
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019 We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes physical and cognitive limitations of the oracle into account when selecting sensor data to be annotated by the oracle.
Hassan Ghasemzadeh, Zhila Esna Ashari
openaire +3 more sources
A Markovian Formalism for Active Querying [PDF]
arXiv, 2023 Active learning algorithms have been an integral part of recent advances in artificial intelligence. However, the research in the field is widely varying and lacks an overall organizing leans. We outline a Markovian formalism for the field of active learning and survey the literature to demonstrate the organizing capability of our proposed formalism ...
arxiv