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 2491–2500 of 3073 papers

TitleStatusHype
Active learning using weakly supervised signals for quality inspection—0
Active Learning via Regression Beyond Realizability—0
Active Learning with a Drifting Distribution—0
Active learning with biased non-response to label requests—0
Active Learning with Combinatorial Coverage—0
Active Learning with Constrained Topic Model—0
Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation—0
Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization—0
Active Learning with Efficient Feature Weighting Methods for Improving Data Quality and Classification Accuracy—0
Active Learning with Expert Advice—0
Show:102550
← PrevPage 250 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