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 1861–1870 of 3569 papers

TitleStatusHype
Next-item Recommendations in Short Sessions—0
Noether Networks: Meta-Learning Useful Conserved Quantities—0
Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings—0
Non-greedy Gradient-based Hyperparameter Optimization Over Long Horizons—0
Nonlinear Meta-Learning Can Guarantee Faster Rates—0
Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony—0
Nonstochastic Bandits with Infinitely Many Experts—0
NormGrad: Finding the Pixels that Matter for Training—0
NORML: Nodal Optimization for Recurrent Meta-Learning—0
NoRML: No-Reward Meta Learning—0
Show:102550
← PrevPage 187 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