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 3411–3420 of 3569 papers

TitleStatusHype
Gradient Agreement as an Optimization Objective for Meta-Learning—0
Incremental Few-Shot Learning with Attention Attractor NetworksCode0
ProMP: Proximal Meta-Policy SearchCode0
A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies—0
Task-Embedded Control Networks for Few-Shot Imitation LearningCode0
Meta-Learning: A Survey—0
AutoLoss: Learning Discrete Schedules for Alternate OptimizationCode0
Unsupervised Learning via Meta-Learning—0
SParse: Ko University Graph-Based Parsing System for the CoNLL 2018 Shared Task—0
Layer-compensated Pruning for Resource-constrained Convolutional Neural NetworksCode0
Show:102550
← PrevPage 342 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