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 2371–2380 of 3569 papers

TitleStatusHype
Meta-Learning for Few-Shot Named Entity Recognition—0
Bayesian Model-Agnostic Meta-Learning with Matrix-Valued Kernels for Quality Estimation—0
Continual Quality Estimation with Online Bayesian Meta-Learning—0
EndTimes at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with BERT and Ensembles—0
Meta-learning for Classifying Previously Unseen Data Source into Previously Unseen Emotional CategoriesCode0
Reconstruction guided Meta-learning for Few Shot Open Set Recognition—0
Bilevel Optimization for Machine Learning: Algorithm Design and Convergence Analysis—0
Adaptive Approach Phase Guidance for a Hypersonic Glider via Reinforcement Meta Learning—0
A Thorough Review on Recent Deep Learning Methodologies for Image Captioning—0
Dataset Distillation with Infinitely Wide Convolutional NetworksCode0
Show:102550
← PrevPage 238 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