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 3421–3430 of 3569 papers

TitleStatusHype
META-DES: A Dynamic Ensemble Selection Framework using Meta-Learning—0
A Better Baseline for Second Order Gradient Estimation in Stochastic Computation Graphs—0
Meta-Learning with Individualized Feature Space for Few-Shot Classification—0
Model-Agnostic Meta-Learning for Multimodal Task Distributions—0
Variadic Learning by Bayesian Nonparametric Deep Embedding—0
CAML: Fast Context Adaptation via Meta-Learning—0
Sample Efficient Adaptive Text-to-Speech—0
Meta Learning with Fast/Slow Learners—0
AutoLoss: Learning Discrete Schedule for Alternate Optimization—0
Correction Networks: Meta-Learning for Zero-Shot Learning—0
Show:102550
← PrevPage 343 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