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 1051–1060 of 3073 papers

TitleStatusHype
Active Learning for Risk-Sensitive Inverse Reinforcement Learning—0
Active Learning For Repairable Hardware Systems With Partial Coverage—0
Active Learning and Discovery of Object Categories in the Presence of Unnameable Instances—0
Comparative Study of Learning Outcomes for Online Learning Platforms—0
Comparison of Grapheme-to-Phoneme Conversion Methods on a Myanmar Pronunciation Dictionary—0
Adversarial Active Learning for Deep Networks: a Margin Based Approach—0
Active Learning for Regression with Aggregated Outputs—0
Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection—0
Active Learning and CSI Acquisition for mmWave Initial Alignment—0
Active Anomaly Detection for time-domain discoveries—0
Show:102550
← PrevPage 106 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