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 1941–1950 of 3073 papers

TitleStatusHype
Statistical Active Learning Algorithms—0
Statistical Active Learning Algorithms for Noise Tolerance and Differential Privacy—0
Statistical Hardware Design With Multi-model Active Learning—0
STAYKATE: Hybrid In-Context Example Selection Combining Representativeness Sampling and Retrieval-based Approach -- A Case Study on Science Domains—0
ST-CoNAL: Consistency-Based Acquisition Criterion Using Temporal Self-Ensemble for Active Learning—0
SteM at SemEval-2016 Task 4: Applying Active Learning to Improve Sentiment Classification—0
Stochastic Adversarial Gradient Embedding for Active Domain Adaptation—0
Stochastic Descent Analysis of Representation Learning Algorithms—0
Stochastic Optimization for Vaccine and Testing Kit Allocation for the COVID-19 Pandemic—0
Stochastic Submodular Maximization via Polynomial Estimators—0
Show:102550
← PrevPage 195 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