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 1561–1570 of 3569 papers

TitleStatusHype
Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery—0
Learning Differential Operators for Interpretable Time Series Modeling—0
Fully Online Meta-Learning Without Task Boundaries—0
Contextual HyperNetworks for Novel Feature Adaptation—0
Learning Effective Exploration Strategies For Contextual Bandits—0
Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy—0
FS-SS: Few-Shot Learning for Fast and Accurate Spike Sorting of High-channel Count Probes—0
Learning Fast Sample Re-weighting Without Reward Data—0
Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning—0
A Framework of Meta Functional Learning for Regularising Knowledge Transfer—0
Show:102550
← PrevPage 157 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