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 1031–1040 of 3073 papers

TitleStatusHype
Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates—0
Active Learning and the Irish Treebank—0
Active learning for sense annotation—0
A framework for the extraction of Deep Neural Networks by leveraging public data—0
Active Learning and Proofreading for Delineation of Curvilinear Structures—0
Active learning and negative evidence for language identification—0
Extended Active Learning Method—0
Active Learning for Segmentation by Optimizing Content Information for Maximal Entropy—0
Active Learning for Segmentation Based on Bayesian Sample Queries—0
A Finite-Horizon Approach to Active Level Set Estimation—0
Show:102550
← PrevPage 104 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