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 2371–2380 of 3073 papers

TitleStatusHype
Active Learning for Network Intrusion Detection—0
Active Learning for Network Traffic Classification: A Technical Study—0
Active Learning for New Domains in Natural Language Understanding—0
Active Learning for NLP with Large Language Models—0
Active Learning for Noisy Data Streams Using Weak and Strong Labelers—0
Active Learning for Nonlinear System Identification with Guarantees—0
Active Learning for Non-Parametric Choice Models—0
Active learning for object detection in high-resolution satellite images—0
Active Learning for Object Detection with Non-Redundant Informative Sampling—0
Active Learning for One-Class Classification Using Two One-Class Classifiers—0
Show:102550
← PrevPage 238 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