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 3271–3280 of 3569 papers

TitleStatusHype
Beyond Exponentially Discounted Sum: Automatic Learning of Return Function—0
Image Deformation Meta-Networks for One-Shot LearningCode0
Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy—0
Discrete Infomax Codes for Supervised Representation Learning—0
Dataset2Vec: Learning Dataset Meta-FeaturesCode0
Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement LearningCode0
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence—0
Unsupervised Intuitive Physics from Past Experiences—0
Personalizing Dialogue Agents via Meta-LearningCode0
Zero-shot task adaptation by homoiconic meta-mappingCode0
Show:102550
← PrevPage 328 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