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 2741–2750 of 3073 papers

TitleStatusHype
Active Decision Boundary Annotation with Deep Generative ModelsCode0
The Relationship Between Agnostic Selective Classification Active Learning and the Disagreement Coefficient—0
Adaptivity to Noise Parameters in Nonparametric Active Learning—0
Visual-Interactive Similarity Search for Complex Objects by Example of Soccer Player Analysis—0
Learning Active Learning from DataCode0
Deep Bayesian Active Learning with Image DataCode0
Active Learning for Cost-Sensitive Classification—0
Active Learning for Accurate Estimation of Linear Models—0
Active Learning Using Uncertainty InformationCode0
Diameter-Based Active Learning—0
Show:102550
← PrevPage 275 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