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 1311–1320 of 3073 papers

TitleStatusHype
Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study—0
DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query—0
DEMAU: Decompose, Explore, Model and Analyse Uncertainties—0
Active Learning from Peers—0
Active Learning-based Isolation Forest (ALIF): Enhancing Anomaly Detection in Decision Support Systems—0
Dependency-aware Maximum Likelihood Estimation for Active Learning—0
Dependency Parsing with Partial Annotations: An Empirical Comparison—0
Depression Symptoms Modelling from Social Media Text: A Semi-supervised Learning Approach—0
Depth Uncertainty Networks for Active Learning—0
Cell Library Characterization for Composite Current Source Models Based on Gaussian Process Regression and Active Learning—0
Show:102550
← PrevPage 132 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