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 1221–1230 of 3073 papers

TitleStatusHype
Deep Active Learning for Text Classification with Diverse Interpretations—0
From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach—0
Deep Active Learning in the Open World—0
Data Shapley Valuation for Efficient Batch Active Learning—0
Data Summarization via Bilevel Optimization—0
Data Uncertainty without Prediction Models—0
Deep Active Learning with Noisy Oracle in Object Detection—0
Congruence-based Learning of Probabilistic Deterministic Finite Automata—0
Adaptive Combinatorial Maximization: Beyond Approximate Greedy Policies—0
ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion—0
Show:102550
← PrevPage 123 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