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 2241–2250 of 3073 papers

TitleStatusHype
Active Deep Kernel Learning of Molecular Functionalities: Realizing Dynamic Structural Embeddings—0
Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls—0
Active Deep Learning for Classification of Hyperspectral Images—0
Active Learning Guided by Efficient Surrogate Learners—0
Active deep learning method for the discovery of objects of interest in large spectroscopic surveys—0
Active Deep Learning on Entity Resolution by Risk Sampling—0
Active Dialogue Simulation in Conversational Systems—0
Active Dictionary Learning in Sparse Representation Based Classification—0
Active Discovery of Network Roles for Predicting the Classes of Network Nodes—0
Active Discriminative Text Representation Learning—0
Show:102550
← PrevPage 225 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