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 1851–1875 of 3073 papers

TitleStatusHype
Active Learning Under Malicious Mislabeling and Poisoning Attacks—0
SoCal: Selective Oracle Questioning for Consistency-based Active Learning of Physiological Signals—0
Efficiently labelling sequences using semi-supervised active learning—0
Deep Active Learning for Object Detection with Mixture Density Networks—0
Better Optimization can Reduce Sample Complexity: Active Semi-Supervised Learning via Convergence Rate Control—0
Learning Active Learning in the Batch-Mode Setup with Ensembles of Active Learning Agents—0
Machine Learning Algorithms for Data Labeling: An Empirical Evaluation—0
On the Geometry of Deep Bayesian Active Learning—0
Least Probable Disagreement Region for Active Learning—0
Learning to Make Decisions via Submodular Regularization—0
Uncertainty-aware Active Learning for Optimal Bayesian Classifier—0
Towards Understanding the Behaviors of Optimal Deep Active Learning AlgorithmsCode1
From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach—0
Whom to Test? Active Sampling Strategies for Managing COVID-19—0
An Active Learning Method for Diabetic Retinopathy Classification with Uncertainty Quantification—0
Active Deep Learning on Entity Resolution by Risk Sampling—0
Self-supervised self-supervision by combining deep learning and probabilistic logic—0
Learning Halfspaces With Membership Queries—0
Multi-fidelity Bayesian Neural Networks: Algorithms and Applications—0
On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise—0
An Information-Theoretic Framework for Unifying Active Learning ProblemsCode0
GLISTER: Generalization based Data Subset Selection for Efficient and Robust LearningCode1
Rebuilding Trust in Active Learning with Actionable Metrics—0
Minimax Active Learning—0
Embodied Visual Active Learning for Semantic Segmentation—0
Show:102550
← PrevPage 75 of 123Next →

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