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 131–140 of 3073 papers

TitleStatusHype
Active Learning for Coreference Resolution using Discrete AnnotationCode1
AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African LanguagesCode1
Differentiable sampling of molecular geometries with uncertainty-based adversarial attacksCode1
Active Learning for BERT: An Empirical StudyCode1
A dynamic Bayesian optimized active recommender system for curiosity-driven Human-in-the-loop automated experimentsCode1
Active Learning for Bayesian 3D Hand Pose EstimationCode1
Active Invariant Causal Prediction: Experiment Selection through StabilityCode1
Active Learning for Computationally Efficient Distribution of Binary Evolution SimulationsCode1
Active Learning for Convolutional Neural Networks: A Core-Set ApproachCode1
A Framework and Benchmark for Deep Batch Active Learning for RegressionCode1
Show:102550
← PrevPage 14 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