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 2891–2900 of 3073 papers

TitleStatusHype
What I've learned about annotating informal text (and why you shouldn't take my word for it)—0
ICE: Rapid Information Extraction Customization for NLP Novices—0
Narrowing the Loop: Integration of Resources and Linguistic Dataset Development with Interactive Machine Learning—0
Efficient Label Collection for Unlabeled Image Datasets—0
Active Learning for Structured Probabilistic Models With Histogram Approximation—0
Active Learning and Discovery of Object Categories in the Presence of Unnameable Instances—0
Learning with a Drifting Target Concept—0
Algorithmic Connections Between Active Learning and Stochastic Convex Optimization—0
An Analysis of Active Learning With Uniform Feature Noise—0
Active learning for sense annotation—0
Show:102550
← PrevPage 290 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