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 1061–1070 of 3073 papers

TitleStatusHype
Margin-based sampling in high dimensions: When being active is less efficient than staying passive—0
An Empirical Study on the Efficacy of Deep Active Learning for Image Classification—0
ALARM: Active LeArning of Rowhammer Mitigations—0
Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning—0
Deep Active Learning for Computer Vision: Past and Future—0
Combining Data Generation and Active Learning for Low-Resource Question AnsweringCode0
Looking at the posterior: accuracy and uncertainty of neural-network predictions—0
Responsible Active Learning via Human-in-the-loop Peer Study—0
Knowledge-Aware Federated Active Learning with Non-IID DataCode1
PyTAIL: Interactive and Incremental Learning of NLP Models with Human in the Loop for Online DataCode1
Show:102550
← PrevPage 107 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