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 1976–2000 of 3073 papers

TitleStatusHype
SUPClust: Active Learning at the Boundaries—0
Superposition through Active Learning lens—0
Supervised Negative Binomial Classifier for Probabilistic Record Linkage—0
Supervising Feature Influence—0
Support Vector Machine Active Learning Algorithms with Query-by-Committee versus Closest-to-Hyperplane Selection—0
Support Vector Machines under Adversarial Label Contamination—0
Surrogate Losses in Passive and Active Learning—0
Sustaining model performance for covid-19 detection from dynamic audio data: Development and evaluation of a comprehensive drift-adaptive framework—0
Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization—0
Synthesizing Video Trajectory Queries—0
Tackling Provably Hard Representative Selection via Graph Neural Networks—0
TActiLE: Tiny Active LEarning for wearable devices—0
Taking into Account the Differences between Actively and Passively Acquired Data: The Case of Active Learning with Support Vector Machines for Imbalanced Datasets—0
Taking the human out of decomposition-based optimization via artificial intelligence: Part II. Learning to initialize—0
Taming Small-sample Bias in Low-budget Active Learning—0
Targeted Active Learning for Bayesian Decision-Making—0
Target-Independent Active Learning via Distribution-Splitting—0
Targeting Optimal Active Learning via Example Quality—0
Targeting the partition function of chemically disordered materials with a generative approach based on inverse variational autoencoders—0
Task-Aware Variational Adversarial Active Learning—0
Task Selection for Bandit-Based Task Assignment in Heterogeneous Crowdsourcing—0
Teacher's Perception in the Classroom—0
Teaching an Active Learner with Contrastive Examples—0
Teaching Digital Signal Processing by Partial Flipping, Active Learning and Visualization—0
Teaching Interactively to Learn Emotions in Natural Language—0
Show:102550
← PrevPage 80 of 123Next →

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