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 3321–3330 of 3569 papers

TitleStatusHype
Guided Evolutionary Strategies: Escaping the curse of dimensionality in random search—0
Learning Unsupervised Learning Rules—0
Transferring SLU Models in Novel Domains—0
Amortized Bayesian Meta-Learning—0
Sample-efficient policy learning in multi-agent Reinforcement Learning via meta-learning—0
Learning to Learn with Conditional Class Dependencies—0
Learning Meta Model for Zero- and Few-shot Face Anti-spoofing—0
META-Learning State-based Eligibility Traces for More Sample-Efficient Policy EvaluationCode0
Hierarchical Meta Learning—0
Meta-Weighted Gaussian Process Experts for Personalized Forecasting of AD Cognitive Changes—0
Show:102550
← PrevPage 333 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