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 1061–1070 of 3073 papers

TitleStatusHype
Active Learning for Direct Preference Optimization—0
Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification—0
Active Learning with Statistical Models—0
Active Learning with Simple Questions—0
Batch Active Learning via Coordinated Matching—0
Batch Active Learning of Reward Functions from Human Preferences—0
Batch Active Learning from the Perspective of Sparse Approximation—0
Active Learning with Safety Constraints—0
Active learning for detection of stance components—0
BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets—0
Show:102550
← PrevPage 107 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