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 3471–3480 of 3569 papers

TitleStatusHype
Meta-Gradient Reinforcement LearningCode0
Been There, Done That: Meta-Learning with Episodic RecallCode0
Meta-Learning Probabilistic Inference For PredictionCode0
Meta-Learning for Low-Resource Neural Machine Translation—0
Multi-task Maximum Entropy Inverse Reinforcement LearningCode0
Meta-Learning with Hessian-Free Approach in Deep Neural Nets TrainingCode0
Task-Agnostic Meta-Learning for Few-shot Learning—0
Diverse Few-Shot Text Classification with Multiple MetricsCode0
Continuous Learning in a Hierarchical Multiscale Neural Network—0
Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examplesCode0
Show:102550
← PrevPage 348 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