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 1741–1750 of 3073 papers

TitleStatusHype
Active Learning in Gaussian Process State Space Model—0
When Deep Learners Change Their Mind: Learning Dynamics for Active Learning—0
Batch Active Learning at ScaleCode0
Robust and Active Learning for Deep Neural Network Regression—0
Self-learning Emulators and Eigenvector Continuation—0
Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning—0
Restless Bandits with Many Arms: Beating the Central Limit Theorem—0
MCDAL: Maximum Classifier Discrepancy for Active LearningCode0
Robust Adaptive Submodular Maximization—0
Active Learning in Incomplete Label Multiple Instance Multiple Label Learning—0
Show:102550
← PrevPage 175 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