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 1451–1475 of 3569 papers

TitleStatusHype
Continual Quality Estimation with Online Bayesian Meta-Learning—0
Information-theoretic Analysis of Test Data Sensitivity in Uncertainty—0
Information-Theoretic Foundations for Machine Learning—0
Information-Theoretic Generalization Bounds for Meta-Learning and Applications—0
Learning Generative Prior with Latent Space Sparsity Constraints—0
Informed Meta-Learning—0
In-Loop Meta-Learning with Gradient-Alignment Reward—0
Deep neural network ensemble by data augmentation and bagging for skin lesion classification—0
Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment—0
InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning—0
INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy—0
Integrated and Adaptive Guidance and Control for Endoatmospheric Missiles via Reinforcement Learning—0
Continual learning under domain transfer with sparse synaptic bursting—0
Integrated Image-Text Based on Semi-supervised Learning for Small Sample Instance Segmentation—0
GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning—0
Intelligent Travel Activity Monitoring: Generalized Distributed Acoustic Sensing Approaches—0
INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks—0
Interactive Graph Convolutional Filtering—0
Interactive singing melody extraction based on active adaptation—0
Interpretable Automated Machine Learning in Maana(TM) Knowledge Platform—0
Continual Few-Shot Learning with Adversarial Class Storage—0
Interpretable Deep Convolutional Neural Networks via Meta-learning—0
Interpretable Meta-Learning of Physical Systems—0
Attribute Propagation Network for Graph Zero-shot Learning—0
A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms—0
Show:102550
← PrevPage 59 of 143Next →
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