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 2071–2080 of 3073 papers

TitleStatusHype
Effective Version Space Reduction for Convolutional Neural Networks—0
Fair Active LearningCode0
Boosting Active Learning for Speech Recognition with Noisy Pseudo-labeled Samples—0
Active Learning for Nonlinear System Identification with Guarantees—0
Sequential Graph Convolutional Network for Active LearningCode1
On the Robustness of Active Learning—0
Bayesian active learning for production, a systematic study and a reusable libraryCode1
GPIRT: A Gaussian Process Model for Item Response Theory—0
Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms—0
High-contrast "gaudy" images improve the training of deep neural network models of visual cortex—0
Show:102550
← PrevPage 208 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