SOTAVerified|Agents Browse Leaderboard About

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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 621–630 of 3569 papers

Title	Date	Tasks	Status	Hype
ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection	May 26, 2019	Deep LearningMeta-Learning	CodeCode Available	1
Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings	Apr 25, 2019	Click-Through Rate PredictionMeta-Learning	CodeCode Available	1
Meta-Learning with Differentiable Convex Optimization	Apr 7, 2019	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available	1
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning	Mar 25, 2019	AutoMLMeta-Learning	CodeCode Available	1
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples	Mar 7, 2019	Few-Shot Image ClassificationGeneral Classification	CodeCode Available	1
Model Primitive Hierarchical Lifelong Reinforcement Learning	Mar 4, 2019	Hierarchical Reinforcement LearningLifelong learning	CodeCode Available	1
Induction Networks for Few-Shot Text Classification	Feb 27, 2019	Few-Shot Text ClassificationGeneral Classification	CodeCode Available	1
Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting	Feb 20, 2019	Image ClassificationMeta-Learning	CodeCode Available	1
Particle Flow Bayes' Rule	Feb 2, 2019	Bayesian InferenceMeta-Learning	CodeCode Available	1
Modular meta-learning in abstract graph networks for combinatorial generalization	Dec 19, 2018	Meta-Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 63 of 357Next →

All datasets ML10 MT50 ML45 OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MZ+Recon	Meta-train success rate	97.8	—	Unverified
2	MZ	Meta-train success rate	97.6	—	Unverified
3	MAML	Meta-test success rate	36	—	Unverified
4	RL^2	Meta-test success rate	10	—	Unverified
5	DnC	Meta-test success rate	5.4	—	Unverified
6	PEARL	Meta-test success rate	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SoftModule	Average Success Rate	60	—	Unverified
2	Multi-task multi-head SAC	Average Success Rate	35.85	—	Unverified
3	DisCor	Average Success Rate	26	—	Unverified
4	NDP	Average Success Rate	11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MZ+Recon	Meta-test success rate (zero-shot)	18.5	—	Unverified
2	MZ	Meta-test success rate (zero-shot)	17.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Metadrop	% Test Accuracy	95.75	—	Unverified