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 1911–1920 of 3073 papers

TitleStatusHype
Information-Theoretic Active Correlation Clustering—0
Effective Data Selection for Seismic Interpretation through Disagreement—0
Effective Evaluation of Deep Active Learning on Image Classification Tasks—0
Effective Version Space Reduction for Convolutional Neural Networks—0
Efficiency of active learning for the allocation of workers on crowdsourced classification tasks—0
Boosting Active Learning for Speech Recognition with Noisy Pseudo-labeled Samples—0
Efficient Active Learning for Gaussian Process Classification by Error Reduction—0
Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network—0
Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach—0
Efficient Active Learning of Halfspaces: an Aggressive Approach—0
Show:102550
← PrevPage 192 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