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 1531–1540 of 3073 papers

TitleStatusHype
Efficient and Reliable Probabilistic Interactive Learning with Structured Outputs—0
Double-Barreled Question Detection at Momentive—0
Fast Rates in Pool-Based Batch Active Learning—0
Improving performance of aircraft detection in satellite imagery while limiting the labelling effort: Hybrid active learning—0
Active Learning Improves Performance on Symbolic RegressionTasks in StackGP—0
Sampling Strategy for Fine-Tuning Segmentation Models to Crisis Area under Scarcity of Data—0
Improving greedy core-set configurations for active learning with uncertainty-scaled distances—0
A Lagrangian Duality Approach to Active Learning—0
LiDAR dataset distillation within bayesian active learning framework: Understanding the effect of data augmentation—0
Improving Probabilistic Models in Text Classification via Active Learning—0
Show:102550
← PrevPage 154 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