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 3401–3410 of 3569 papers

TitleStatusHype
Guiding Policies with Language via Meta-LearningCode0
Learning to Bound the Multi-class Bayes Error—0
Transformative Machine Learning—0
Meta-Learning for Multi-objective Reinforcement Learning—0
On Meta-Learning for Dynamic Ensemble Selection—0
META-DES.Oracle: Meta-learning and feature selection for ensemble selection—0
META-DES.H: a dynamic ensemble selection technique using meta-learning and a dynamic weighting approach—0
RELF: Robust Regression Extended with Ensemble Loss Function—0
Truncated Back-propagation for Bilevel OptimizationCode0
Meta-Learning Multi-task Communication—0
Show:102550
← PrevPage 341 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