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 1511–1520 of 3073 papers

TitleStatusHype
Active Learning for Argument Mining: A Practical Approach—0
Evaluating Active Learning Heuristics for Sequential Diagnosis—0
Evaluating Sentence-Level Relevance Feedback for High-Recall Information Retrieval—0
Evaluating the effect of data augmentation and BALD heuristics on distillation of Semantic-KITTI dataset—0
Evaluating Unsupervised Language Model Adaptation Methods for Speaking Assessment—0
Evaluating Zero-cost Active Learning for Object Detection—0
Evaluation of Seed Set Selection Approaches and Active Learning Strategies in Predictive Coding—0
Evaluation of uncertainty estimations for Gaussian process regression based machine learning interatomic potentials—0
Events Beyond ACE: Curated Training for Events—0
Composable Core-sets for Diversity Approximation on Multi-Dataset Streams—0
Show:102550
← PrevPage 152 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