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 1991–2000 of 3569 papers

TitleStatusHype
Pre-training Text Representations as Meta Learning—0
Principal component analysis for Gaussian process posteriors—0
Prior Knowledge for Few-shot Learning—Inductive Reasoning and Distribution Calibration—0
Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning—0
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components—0
PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies—0
Probabilistic Meta-Learning for Bayesian Optimization—0
Probabilistic Model-Agnostic Meta-Learning—0
Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process—0
problexity -- an open-source Python library for binary classification problem complexity assessment—0
Show:102550
← PrevPage 200 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