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 151–160 of 3073 papers

Title	Date	Tasks	Status	Hype
Bayesian Active Learning with Fully Bayesian Gaussian Processes	May 20, 2022	Active LearningGaussian Processes	CodeCode Available	1
Self-supervised Assisted Active Learning for Skin Lesion Segmentation	May 14, 2022	Active LearningDiversity	CodeCode Available	1
Towards Computationally Feasible Deep Active Learning	May 7, 2022	Active Learningtext-classification	CodeCode Available	1
Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning (Replicability Study)	May 2, 2022	Active LearningUncertainty Quantification	CodeCode Available	1
Active Learning Helps Pretrained Models Learn the Intended Task	Apr 18, 2022	Active Learning	CodeCode Available	1
Graph-based Active Learning for Semi-supervised Classification of SAR Data	Mar 31, 2022	Active Learninggraph construction	CodeCode Available	1
Active Learning for Computationally Efficient Distribution of Binary Evolution Simulations	Mar 30, 2022	Active Learningregression	CodeCode Available	1
A Comparative Survey of Deep Active Learning	Mar 25, 2022	Active LearningSurvey	CodeCode Available	1
A Framework and Benchmark for Deep Batch Active Learning for Regression	Mar 17, 2022	Active Learningregression	CodeCode Available	1
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy	Mar 15, 2022	Active LearningClassification	CodeCode Available	1

Show:10 25 50

← PrevPage 16 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