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 601–610 of 3073 papers

TitleStatusHype
ALLSH: Active Learning Guided by Local Sensitivity and Hardness—0
Active Learning in Symbolic Regression with Physical Constraints—0
Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets—0
Active Learning by Query by Committee with Robust Divergences—0
Active Learning in Recommendation Systems with Multi-level User Preferences—0
Active Learning in Physics: From 101, to Progress, and Perspective—0
Bounded Expectation of Label Assignment: Dataset Annotation by Supervised Splitting with Bias-Reduction Techniques—0
Active Continual Learning: On Balancing Knowledge Retention and Learnability—0
Active Learning in Noisy Conditions for Spoken Language Understanding—0
ACIL: Active Class Incremental Learning for Image Classification—0
Show:102550
← PrevPage 61 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