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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1661–1670 of 3073 papers

Title	Date	Tasks	Status	Hype
Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)	Jul 6, 2021	Active Learning	—Unverified	0
Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering	Jul 6, 2021	Active LearningObject Recognition	CodeCode Available	1
Near-optimal inference in adaptive linear regression	Jul 5, 2021	Active Learningregression	—Unverified	0
Matching a Desired Causal State via Shift Interventions	Jul 5, 2021	Active Learning	CodeCode Available	0
Knowledge Modelling and Active Learning in Manufacturing	Jul 5, 2021	Active LearningFriction	—Unverified	0
Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes	Jul 4, 2021	Active LearningDiversity	—Unverified	0
Active Learning of Abstract Plan Feasibility	Jul 1, 2021	Active Learning	—Unverified	0
SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios	Jul 1, 2021	Active Learningimage-classification	CodeCode Available	1
Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity	Jul 1, 2021	Active LearningBIG-bench Machine Learning	—Unverified	0
On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction	Jun 29, 2021	Active LearningGraph Neural Network	CodeCode Available	0

Show:10 25 50

← PrevPage 167 of 308Next →

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	TypiClust	Accuracy	93.2	—	Unverified
2	PT4AL	Accuracy	93.1	—	Unverified
3	Learning loss	Accuracy	91.01	—	Unverified
4	CoreGCN	Accuracy	90.7	—	Unverified
5	Core-set	Accuracy	89.92	—	Unverified
6	Random Baseline (Resnet18)	Accuracy	88.45	—	Unverified
7	Random Baseline (VGG16)	Accuracy	85.09	—	Unverified