Results 301 to 310 of about 11,061,910 (343)

Does Active Learning Work? A Review of the Research

Journal of Engineering Education, 2004
Michael Prince
exaly   +2 more sources

To Actively Initialize Active Learning

Pattern Recognition, 2022
Though much effort has been spent on designing new active learning algorithms, little attention has been paid to the initialization problem of active learning, i.e., how to find a set of labeled samples which contains at least one instance per category. This work identifies the initialization of active learning as a separate and novel research problem,
Yazhou Yang, Marco Loog
openaire   +3 more sources

Active Learning by Learning

Proceedings of the AAAI Conference on Artificial Intelligence, 2015
Pool-based active learning is an important technique that helps reduce labeling efforts within a pool of unlabeled instances. Currently, most pool-based active learning strategies are constructed based on some human-designed philosophy; that is, they reflect what human beings assume to be “good labeling questions.” However, while such ...
Wei-Ning Hsu, Hsuan-Tien Lin
openaire   +1 more source

Re-Active Learning: Active Learning with Relabeling

Proceedings of the AAAI Conference on Artificial Intelligence, 2016
Active learning seeks to train the best classifier at the lowest annotation cost by intelligently picking the best examples to label. Traditional algorithms assume there is a single annotator and disregard the possibility of requesting additional independent annotations for a previously labeled example.
Christopher H. Lin, Mausam, Daniel S. Weld   +2 more
openaire   +1 more source

Deep Bayesian Active Learning with Image Data

International Conference on Machine Learning, 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.
Y. Gal, Riashat Islam, Zoubin Ghahramani
semanticscholar   +1 more source

Active Learning on WEB

International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06), 2006
Distance learning is increasing in popularity, especially as research proves that learning can be at least as effective from a distance as it is face-to-face. As it becomes apparent that technology neither hinders nor assist the effectiveness of the learning, our focus shifts to instructional design considerations contribute to effective distance ...
Basak, Havva H., Cakir, Sen
openaire   +2 more sources

Workshop: Learning agile through active learning activities

2012 Frontiers in Education Conference Proceedings, 2012
Games and simulation are a great way to learn theories and new behaviors that can be applied to software engineering activities. The presenters are going to teach three games that can be used in a software engineering course or any course that deals with agile methods. The presenters will talk about the benefits of agile development and how these games
Jennifer A. Polack-Wahl, Karen Anewalt
openaire   +1 more source

Active learning-assisted directed evolution

bioRxiv
Directed evolution (DE) is a powerful tool to optimize protein fitness for a specific application. However, DE can be inefficient when mutations exhibit non-additive, or epistatic, behavior.
Jason Yang, Ravi G. Lal, James C. Bowden, Raul Astudillo, Mikhail A. Hameedi, Sukhvinder Kaur, Matthew Hill, Yisong Yue, Frances H. Arnold   +8 more
semanticscholar   +1 more source

Anytime Active Learning

Proceedings of the AAAI Conference on Artificial Intelligence, 2014
A common bottleneck in deploying supervised learning systems is collecting human-annotated examples. In many domains, annotators form an opinion about the label of an example incrementally -- e.g., each additional word read from a document or each additional minute spent inspecting a video helps inform the annotation. In this paper, we
Maria Eugenia Ramirez-Loaiza, Aron Culotta, Mustafa Bilgic 0001   +2 more
openaire   +1 more source