SOTAVerified

Active Learning

Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model

Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1661–1670 of 3073 papers

TitleStatusHype
Uncertainty Estimation for Language Reward Models—0
Uncertainty for Active Learning on Graphs—0
Uncertainty Herding: One Active Learning Method for All Label Budgets—0
Uncertainty in Natural Language Generation: From Theory to Applications—0
Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection—0
Uncertainty Modeling for Machine Comprehension Systems using Efficient Bayesian Neural Networks—0
Uncertainty quantification and exploration-exploitation trade-off in humans—0
Uncertainty Quantification in Continual Open-World Learning—0
Uncertainty Quantification in Graph Neural Networks with Shallow Ensembles—0
Uncertainty Sentence Sampling by Virtual Adversarial Perturbation—0
Show:102550
← PrevPage 167 of 308Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TypiClustAccuracy93.2—Unverified
2PT4ALAccuracy93.1—Unverified
3Learning lossAccuracy91.01—Unverified
4CoreGCNAccuracy90.7—Unverified
5Core-setAccuracy89.92—Unverified
6Random Baseline (Resnet18)Accuracy88.45—Unverified
7Random Baseline (VGG16)Accuracy85.09—Unverified