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 3031–3040 of 3073 papers

TitleStatusHype
Efficient Active Learning of Halfspaces: an Aggressive Approach—0
Surrogate Losses in Passive and Active Learning—0
Active Learning for Imbalanced Sentiment Classification—0
Active Learning with Transfer Learning—0
Batch Active Learning via Coordinated Matching—0
UPM system for WMT 2012—0
Exploring Label Dependency in Active Learning for Phenotype Mapping—0
Active Learning for Coreference Resolution—0
Active Learning for Coreference Resolution—0
DutchSemCor: Targeting the ideal sense-tagged corpus—0
Show:102550
← PrevPage 304 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