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 2451–2460 of 3073 papers

TitleStatusHype
Active Learning of Dynamics Using Prior Domain Knowledge in the Sampling Process—0
Active Learning of General Halfspaces: Label Queries vs Membership Queries—0
Active Learning of Linear Embeddings for Gaussian Processes—0
Active Learning of Mealy Machines with Timers—0
Active Learning of Model Evidence Using Bayesian Quadrature—0
Active Learning of Multi-Index Function Models—0
Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations—0
Active learning of neural population dynamics using two-photon holographic optogenetics—0
Active learning of neural response functions with Gaussian processes—0
Active Learning of Ordinal Embeddings: A User Study on Football Data—0
Show:102550
← PrevPage 246 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