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 1141–1150 of 3073 papers

Title	Date	Tasks	Status	Hype
TiDAL: Learning Training Dynamics for Active Learning	Oct 13, 2022	Active Learning	CodeCode Available	0
Efficient Bayesian Updates for Deep Learning via Laplace Approximations	Oct 12, 2022	Active LearningDeep Learning	CodeCode Available	1
VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation	Oct 12, 2022	Active LearningHand Pose Estimation	CodeCode Available	1
JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks	Oct 12, 2022	Active LearningGraph Mining	—Unverified	0
Deep Active Ensemble Sampling For Image Classification	Oct 11, 2022	Active LearningClassification	—Unverified	0
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes	Oct 11, 2022	Active LearningKnowledge Distillation	—Unverified	0
Few-Shot Continual Active Learning by a Robot	Oct 9, 2022	Active LearningContinual Learning	—Unverified	0
PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design	Oct 8, 2022	Active LearningBayesian Optimization	—Unverified	0
Is margin all you need? An extensive empirical study of active learning on tabular data	Oct 7, 2022	Active LearningAll	—Unverified	0
To Softmax, or not to Softmax: that is the question when applying Active Learning for Transformer Models	Oct 6, 2022	Active Learning	CodeCode Available	0

Show:10 25 50

← PrevPage 115 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