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 2961–2970 of 3073 papers

TitleStatusHype
Active Learning with Efficient Feature Weighting Methods for Improving Data Quality and Classification Accuracy—0
Active Learning with Constrained Topic Model—0
Active Semi-Supervised Learning Using Sampling Theory for Graph SignalsCode0
Language Resource Addition: Dictionary or Corpus?—0
A Quality-based Active Sample Selection Strategy for Statistical Machine Translation—0
Focusing Annotation for Semantic Role Labeling—0
Active Learning for Undirected Graphical Model Selection—0
A Compression Technique for Analyzing Disagreement-Based Active Learning—0
Active Learning for Post-Editing Based Incrementally Retrained MT—0
Confidence-based Active Learning Methods for Machine Translation—0
Show:102550
← PrevPage 297 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