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 1281–1290 of 3073 papers

TitleStatusHype
Active Learning by Query by Committee with Robust Divergences—0
Fast Uncertainty Estimates in Deep Learning Interatomic Potentials—0
Active Learning with Expected Error Reduction—0
Can Strategic Data Collection Improve the Performance of Poverty Prediction Models?—0
ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials DataCode0
MEAL: Stable and Active Learning for Few-Shot PromptingCode0
Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions—0
An Efficient Active Learning Pipeline for Legal Text Classification—0
ALANNO: An Active Learning Annotation System for Mortals—0
Understanding Approximation for Bayesian Inference in Neural Networks—0
Show:102550
← PrevPage 129 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