SOTAVerified

Meta-Learning

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2721–2730 of 3569 papers

TitleStatusHype
Meta-Learning Guided Label Noise Distillation for Robust Signal Modulation Classification—0
Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning—0
Meta-Learning Hypothesis Spaces for Sequential Decision-making—0
Meta-Learning Improves Lifelong Relation Extraction—0
Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Review—0
Meta Learning in Bandits within Shared Affine Subspaces—0
Meta Learning in Decentralized Neural Networks: Towards More General AI—0
Meta-learning in healthcare: A survey—0
Meta-Learning Initializations for Interactive Medical Image Registration—0
Meta-learning in natural and artificial intelligence—0
Show:102550
← PrevPage 273 of 357Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified