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 1621–1630 of 3073 papers

TitleStatusHype
Online Learning of Non-Markovian Reward Models—0
Learning Novel Objects Continually Through Curiosity—0
Online Submodular Set Cover, Ranking, and Repeated Active Learning—0
Online Tool Condition Monitoring Based on Parsimonious Ensemble+—0
On Locality in Graph Learning via Graph Neural Network—0
On Machine Learning Approaches for Protein-Ligand Binding Affinity Prediction—0
On Measuring and Quantifying Performance: Error Rates, Surrogate Loss, and an Example in SSL—0
On risk-based active learning for structural health monitoring—0
On robust risk-based active-learning algorithms for enhanced decision support—0
On State Variables, Bandit Problems and POMDPs—0
Show:102550
← PrevPage 163 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