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 391–400 of 3073 papers

TitleStatusHype
Active Learning with Oracle Epiphany—0
Active Learning for Crowd-Sourced Databases—0
Active Learning for Cost-Sensitive Classification—0
Active Discriminative Text Representation Learning—0
Correlation Clustering with Active Learning of Pairwise Similarities—0
Active Learning for Coreference Resolution—0
Active Discovery of Network Roles for Predicting the Classes of Network Nodes—0
Active Learning for Coreference Resolution—0
A Compression Technique for Analyzing Disagreement-Based Active Learning—0
A Bayesian Framework for Active Tactile Object Recognition, Pose Estimation and Shape Transfer Learning—0
Show:102550
← PrevPage 40 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