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 2521–2530 of 3073 papers

TitleStatusHype
Events Beyond ACE: Curated Training for Events—0
Query-Efficient Black-Box Attack by Active Learning—0
Bayesian Semi-supervised Learning with Graph Gaussian ProcessesCode0
Physics-Information-Aided Kriging: Constructing Covariance Functions using Stochastic Simulation Models—0
Learning Time Dependent Choice—0
Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection—0
Information-Theoretic Active Learning for Content-Based Image RetrievalCode0
What do I Annotate Next? An Empirical Study of Active Learning for Action Localization—0
Learning a Policy for Opportunistic Active Learning—0
APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement LearningCode0
Show:102550
← PrevPage 253 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