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 3231–3240 of 3569 papers

TitleStatusHype
Meta-Learning for Black-box Optimization—0
Evolvability ES: Scalable and Direct Optimization of EvolvabilityCode0
Seeker based Adaptive Guidance via Reinforcement Meta-Learning Applied to Asteroid Close Proximity Operations—0
A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning—0
Few-Shot Representation Learning for Out-Of-Vocabulary WordsCode0
Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision—0
Two-stage Optimization for Machine Learning WorkflowCode0
Difficulty-aware Meta-learning for Rare Disease Diagnosis—0
Learning to Cope with Adversarial Attacks—0
Training an Interactive Helper—0
Show:102550
← PrevPage 324 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