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 2261–2270 of 3569 papers

TitleStatusHype
Darts: User-Friendly Modern Machine Learning for Time Series—0
A Meta-learning Approach to Reservoir Computing: Time Series Prediction with Limited Data—0
Online Hyperparameter Meta-Learning with Hypergradient Distillation—0
MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel WeightingCode0
Behaviour-conditioned policies for cooperative reinforcement learning tasks—0
Meta-Reinforcement Learning via Buffering Graph Signatures for Live Video Streaming EventsCode0
An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset—0
Predicting Flat-Fading Channels via Meta-Learned Closed-Form Linear Filters and Equilibrium PropagationCode0
Terminal Adaptive Guidance for Autonomous Hypersonic Strike Weapons via Reinforcement Learning—0
Home Appliance Review Research Via Adversarial Reptile—0
Show:102550
← PrevPage 227 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