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 2451–2500 of 3073 papers

TitleStatusHype
Active learning for binary classification with variable selection—0
Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector—0
Limitations of Assessing Active Learning Performance at Runtime—0
Stopping Active Learning based on Predicted Change of F Measure for Text Classification—0
The Use of Unlabeled Data versus Labeled Data for Stopping Active Learning for Text Classification—0
What does the free energy principle tell us about the brain?—0
Cascade Submodular Maximization: Question Selection and Sequencing in Online Personality Quiz—0
Active Learning with Gaussian Processes for High Throughput PhenotypingCode0
Diverse mini-batch Active Learning—0
ALiPy: Active Learning in PythonCode0
Active Learning for One-Class Classification Using Two One-Class Classifiers—0
Guess What's on my Screen? Clustering Smartphone Screenshots with Active Learning—0
Risk-Aware Active Inverse Reinforcement LearningCode0
Efforts estimation of doctors annotating medical image—0
Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision—0
Active Learning with TensorBoard Projector—0
An Active Learning Framework for Efficient Robust Policy Search—0
Weakly Supervised Active Learning with Cluster Annotation—0
A General Approach to Domain Adaptation with Applications in Astronomy—0
Active Learning and CSI Acquisition for mmWave Initial Alignment—0
Machine Learning for Molecular Dynamics on Long Timescales—0
Molecular Dynamics with Neural-Network Potentials—0
Deep Active Learning for Video-based Person Re-identification—0
SMART: An Open Source Data Labeling Platform for Supervised Learning—0
Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization—0
Active Learning Methods based on Statistical Leverage Scores—0
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One LossCode0
Crowd Sourcing based Active Learning Approach for Parking Sign Recognition—0
Active Learning for Non-Parametric Regression Using Purely Random TreesCode0
Interactive Structure Learning with Structural Query-by-Committee—0
Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian OptimisationCode0
Explore-Exploit: A Framework for Interactive and Online Learning—0
Learning to Caption Images through a Lifetime by Asking QuestionsCode0
Are All Training Examples Created Equal? An Empirical Study—0
Active Learning in Recommendation Systems with Multi-level User Preferences—0
Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer VisionCode0
The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning—0
HS^2: Active Learning over Hypergraphs—0
Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence—0
Robust Active Learning for Electrocardiographic Signal Classification—0
Computer-Assisted Fraud Detection, From Active Learning to Reward Maximization—0
Deep Active Learning with a Neural Architecture SearchCode0
Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy LearningCode0
SHINRA: Structuring Wikipedia by Collaborative Contribution—0
Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensembles—0
Large-Scale Visual Active Learning with Deep Probabilistic Ensembles—0
Active Learning using Deep Bayesian Networks for Surgical Workflow Analysis—0
Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization—0
Exploring Connections Between Active Learning and Model Extraction—0
Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls—0
Show:102550
← PrevPage 50 of 62Next →

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