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 1576–1600 of 3073 papers

TitleStatusHype
Neural Active Learning Meets the Partial Monitoring Framework—0
Neural Active Learning with Performance Guarantees—0
Neural Network-Based Active Learning in Multivariate Calibration—0
Neural Window Decoder for SC-LDPC Codes—0
NeuroADDA: Active Discriminative Domain Adaptation in Connectomic—0
NEXT: A System for Real-World Development, Evaluation, and Application of Active Learning—0
NIL\_UCM: Extracting Drug-Drug interactions from text through combination of sequence and tree kernels—0
Noise-adaptive Margin-based Active Learning and Lower Bounds under Tsybakov Noise Condition—0
Noise-tolerant, Reliable Active Classification with Comparison Queries—0
Noisy Generalized Binary Search—0
Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity—0
Nonparametric active learning for cost-sensitive classification—0
Nonparametric adaptive active learning under local smoothness condition—0
Not All are Made Equal: Consistency of Weighted Averaging Estimators Under Active Learning—0
NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coverage—0
Nuances in Margin Conditions Determine Gains in Active Learning—0
Nuclear Discrepancy for Active Learning—0
O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks—0
OASIS: An Active Framework for Set Inversion—0
Ocean Data Quality Assessment through Outlier Detection-enhanced Active Learning—0
Offline EEG-Based Driver Drowsiness Estimation Using Enhanced Batch-Mode Active Learning (EBMAL) for Regression—0
Omnibus Dropout for Improving The Probabilistic Classification Outputs of ConvNets—0
Omni-Mol: Exploring Universal Convergent Space for Omni-Molecular Tasks—0
On Active Learning for Gaussian Process-based Global Sensitivity Analysis—0
On Computability, Learnability and Extractability of Finite State Machines from Recurrent Neural Networks—0
Show:102550
← PrevPage 64 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