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 2091–2100 of 3073 papers

TitleStatusHype
Deep Active Learning via Open Set RecognitionCode0
Active learning of timed automata with unobservable resets—0
Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning—0
Discovering Knowledge Graph Schema from Short Natural Language Text via Dialog—0
Sampling from a k-DPP without looking at all items—0
Functional MRI applications for psychiatric disease subtyping: a review—0
Similarity Search for Efficient Active Learning and Search of Rare Concepts—0
Motor cortex mapping using active gaussian processes—0
Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification—0
Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples—0
Show:102550
← PrevPage 210 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