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 3511–3520 of 3569 papers

TitleStatusHype
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes TheoryCode0
Rate-optimal Meta Learning of Classification Error—0
Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm—0
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions—0
Meta Learning Shared HierarchiesCode0
Meta-Learning via Feature-Label Memory Network—0
Continuous Adaptation via Meta-Learning in Nonstationary and Competitive EnvironmentsCode0
Supplementary Meta-Learning: Towards a Dynamic Model for Deep Neural Networks—0
Cost Adaptation for Robust Decentralized Swarm BehaviourCode0
Online Learning of a Memory for Learning RatesCode0
Show:102550
← PrevPage 352 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