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 481–490 of 3073 papers

TitleStatusHype
Active Learning for Event Extraction with Memory-based Loss Prediction Model—0
Active Model Aggregation via Stochastic Mirror Descent—0
Active Learning for Fair and Stable Online Allocations—0
Active Multi-Information Source Bayesian Quadrature—0
Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification—0
Active Multi-Task Representation Learning—0
Active Nearest-Neighbor Learning in Metric Spaces—0
Active Learning over DNN: Automated Engineering Design Optimization for Fluid Dynamics Based on Self-Simulated Dataset—0
Active Neural 3D Reconstruction with Colorized Surface Voxel-based View Selection—0
NE-LP: Normalized Entropy and Loss Prediction based Sampling for Active Learning in Chinese Word Segmentation on EHRs—0
Show:102550
← PrevPage 49 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