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 3311–3320 of 3569 papers

TitleStatusHype
Meta-learners' learning dynamics are unlike learners'—0
Modulating transfer between tasks in gradient-based meta-learning—0
MahiNet: A Neural Network for Many-Class Few-Shot Learning with Class Hierarchy—0
Learning a Meta-Solver for Syntax-Guided Program Synthesis—0
Meta-Learning to Guide Segmentation—0
Learning from Noisy Demonstration Sets via Meta-Learned Suitability Assessor—0
Meta-Learning with Domain Adaptation for Few-Shot Learning under Domain Shift—0
Projective Subspace Networks For Few-Shot Learning—0
Attentive Task-Agnostic Meta-Learning for Few-Shot Text Classification—0
Learning to Reinforcement Learn by Imitation—0
Show:102550
← PrevPage 332 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