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 1–10 of 3569 papers

TitleStatusHype
Are encoders able to learn landmarkers for warm-starting of Hyperparameter Optimization?—0
CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy LabelsCode0
Imbalanced Regression Pipeline RecommendationCode0
Mixture of Experts in Large Language Models—0
Iceberg: Enhancing HLS Modeling with Synthetic DataCode0
Meta-Reinforcement Learning for Fast and Data-Efficient Spectrum Allocation in Dynamic Wireless Networks—0
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry DetectionCode0
The Bayesian Approach to Continual Learning: An Overview—0
A statistical physics framework for optimal learning—0
CHOMET: Conditional Handovers via Meta-Learning—0
Show:102550
← PrevPage 1 of 357Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified