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 2931–2940 of 3569 papers

TitleStatusHype
Meta-Learning Bandit Policies by Gradient Ascent—0
Multi-step Estimation for Gradient-based Meta-learning—0
A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton—0
UFO-BLO: Unbiased First-Order Bilevel Optimization—0
Brain-inspired global-local learning incorporated with neuromorphic computing—0
Meta-Model-Based Meta-Policy Optimization—0
Meta Dialogue Policy Learning—0
Meta Learning as Bayes Risk Minimization—0
Interpretable Meta-Measure for Model PerformanceCode0
Learning to Optimize on SPD Manifolds—0
Show:102550
← PrevPage 294 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