Improved dataset characterisation for meta-learning

DOI10.1007/3-540-36182-0_14MaRDI QIDQ4420648zbMATH OpenFDO

Authors Yonghong Peng, Peter Flach, Carlos Soares, Pavel Brazdil

Publication date 18 August 2003

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2534/25340141.htm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Dataset2Vec: learning dataset meta-features
• Feature selection for meta-learning
• Complexity measures for meta-learning and their optimality
• Meta-data: Characterization of input features for meta-learning
• Data complexity meta-features for regression problems

Cited in

(6)

• Instance spaces for machine learning classification
• Dataset2Vec: learning dataset meta-features
• On normalization and algorithm selection for unsupervised outlier detection
• Feature selection for meta-learning
• Meta-data: Characterization of input features for meta-learning
• Towards well-generalizing meta-learning via adversarial task augmentation

This page was built for publication: Improved dataset characterisation for meta-learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4420648)