Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach

DOI10.1007/s10994-019-05838-7zbMath1442.68209OpenAlexW2979324907WikidataQ127110884 ScholiaQ127110884MaRDI QIDQ2183600

Xiang-Rong Sheng, De-Chuan Zhan, Han-Jia Ye

Publication date: 27 May 2020

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-019-05838-7

zbMATH Keywords

supervised learningmulti-task learningmeta-learningfew-shot learningtask-specific

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items

Few-shot learning for spatial regression via neural embedding-based Gaussian processes ⋮ Towards interpreting deep neural networks via layer behavior understanding

Uses Software

• ImageNet
• Adam
• Tensor2Tensor
• Caltech-UCSD Birds
• Omniglot
• AlexNet
• Tunability

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Transfer bounds for linear feature learning
• Logical vision: one-shot meta-interpretive learning from real images
• Face recognition from a single image per person: a survey
• Human-level concept learning through probabilistic program induction