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 3291–3300 of 3569 papers

TitleStatusHype
Efficient Optimization of Loops and Limits with Randomized Telescoping SumsCode0
Enabling Continual Learning in Neural Networks with Meta Learning—0
A Meta Understanding of Meta-Learning—0
Deep Compressed SensingCode0
LEAF: A Benchmark for Federated Settings—0
Meta-Teaching: Curriculum Generation for Lifelong Learning—0
Learning to learn to communicate—0
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment—0
LGM-Net: Learning to Generate Matching Networks for Few-Shot LearningCode0
Meta reinforcement learning as task inferenceCode0
Show:102550
← PrevPage 330 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