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 1776–1800 of 3073 papers

TitleStatusHype
Multiple instance active learning for object detectionCode1
Fast Design Space Exploration of Nonlinear Systems: Part II—0
Optimal Sampling Gaps for Adaptive Submodular Maximization—0
Automated Performance Testing Based on Active Deep LearningCode0
Fast Design Space Exploration of Nonlinear Systems: Part I—0
Stopping Criterion for Active Learning Based on Error StabilityCode0
Efficacy of Bayesian Neural Networks in Active LearningCode0
STARdom: an architecture for trusted and secure human-centered manufacturing systems—0
Paladin: an annotation tool based on active and proactive learning—0
RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learning—0
Is segmentation uncertainty useful?Code1
Active Learning for Deep Object Detection via Probabilistic ModelingCode1
Towards Active Learning Based Smart Assistant for Manufacturing—0
Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation—0
Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries—0
Active Structure Learning of Bayesian Networks in an Observational SettingCode0
Data driven semi-supervised learning—0
Consistency-based Active Learning for Object DetectionCode1
Learning Novel Objects Continually Through Curiosity—0
Active^2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation—0
Active Testing: Sample-Efficient Model EvaluationCode1
Continual Developmental Neurosimulation Using Embodied Computational AgentsCode0
Discrepancy-Based Active Learning for Domain AdaptationCode1
Probabilistic Inference for Structural Health Monitoring: New Modes of Learning from Data—0
Feedback Coding for Active LearningCode0
Show:102550
← PrevPage 72 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