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 1471–1480 of 3569 papers

TitleStatusHype
Learning Neural Processes on the Fly—0
Interpretable Deep Convolutional Neural Networks via Meta-learning—0
Interpretable Meta-Learning of Physical Systems—0
Attribute Propagation Network for Graph Zero-shot Learning—0
Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online—0
Continual learning under domain transfer with sparse synaptic bursting—0
GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning—0
Introducing Symmetries to Black Box Meta Reinforcement Learning—0
Continual Few-Shot Learning with Adversarial Class Storage—0
A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms—0
Show:102550
← PrevPage 148 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