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 3501–3550 of 3569 papers

TitleStatusHype
Visual Question Answering as a Meta Learning Task—0
Learning to Compare: Relation Network for Few-Shot LearningCode1
On Extending Neural Networks with Loss Ensembles for Text Classification—0
Fast Meta-Learning for Adaptive Hierarchical Classifier DesignCode0
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
Hyperparameter Importance Across DatasetsCode1
Learning to Generalize: Meta-Learning for Domain GeneralizationCode1
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
One-Shot Visual Imitation Learning via Meta-LearningCode0
Meta-QSAR: a large-scale application of meta-learning to drug design and discovery—0
ALCN: Meta-Learning for Contrast Normalization Applied to Robust 3D Pose Estimation—0
Meta-Learning MCMC Proposals—0
Meta-SGD: Learning to Learn Quickly for Few-Shot LearningCode1
A Simple Neural Attentive Meta-LearnerCode0
Labeled Memory Networks for Online Model Adaptation—0
Learning to Learn: Meta-Critic Networks for Sample Efficient Learning—0
A Meta-Learning Approach to One-Step Active Learning—0
Exploring the similarity of medical imaging classification problemsCode0
Meta learning Framework for Automated Driving—0
Meta-Learning for Resampling Recommendation SystemsCode0
Gradient Estimators for Implicit ModelsCode0
REMIX: Automated Exploration for Interactive Outlier Detection—0
Probabilistic Matrix Factorization for Automated Machine LearningCode0
One-Shot Imitation Learning—0
Prototypical Networks for Few-shot LearningCode2
RECOD Titans at ISIC Challenge 2017Code0
Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksCode1
Meta NetworksCode0
Online Meta-learning by Parallel Algorithm Competition—0
Learning to Multi-Task by Active SamplingCode0
A Stylometric Inquiry into Hyperpartisan and Fake NewsCode0
Minimally Naturalistic Artificial Intelligence—0
Set2Model Networks: Learning Discriminatively To Learn Generative Models—0
Learning to reinforcement learnCode0
Learning to Learn Neural Networks—0
Active exploration in parameterized reinforcement learningCode0
Fast Image Classification by Boosting Fuzzy Classifiers—0
A Greedy Approach to Adapting the Trace Parameter for Temporal Difference LearningCode0
Learning to learn by gradient descent by gradient descentCode0
Bending the Curve: Improving the ROC Curve Through Error Redistribution—0
Meta-learning within Projective Simulation—0
Adaptive Ensemble Learning with Confidence Bounds—0
Show:102550
← PrevPage 71 of 72Next →
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