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 3001–3025 of 3073 papers

TitleStatusHype
Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition—0
Continuous Active Learning Using Pretrained Transformers—0
Contrastive Coding for Active Learning Under Class Distribution Mismatch—0
Convergence of Uncertainty Sampling for Active Learning—0
Convergence Rates of Active Learning for Maximum Likelihood Estimation—0
Convergence rates of sub-sampled Newton methods—0
CORA: A Deep Active Learning Covid-19 Relevancy Algorithm to Identify Core Scientific Articles—0
Coresets for Classification -- Simplified and Strengthened—0
Coresets for Classification – Simplified and Strengthened—0
Correlation-aware active learning for surgery video segmentation—0
Corruption Robust Active Learning—0
Cost-Aware Query Policies in Active Learning for Efficient Autonomous Robotic Exploration—0
Cost-Based Budget Active Learning for Deep Learning—0
Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning—0
Cost-Effective Training in Low-Resource Neural Machine Translation—0
Cost-Effective Training in Low-Resource Neural Machine Translation—0
Cost-effective Variational Active Entity Resolution—0
Cost-efficient segmentation of electron microscopy images using active learning—0
Cost-Quality Adaptive Active Learning for Chinese Clinical Named Entity Recognition—0
Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection—0
Cost-Sensitive Active Learning for Dialogue State Tracking—0
CoTAL: Human-in-the-Loop Prompt Engineering, Chain-of-Thought Reasoning, and Active Learning for Generalizable Formative Assessment Scoring—0
Counterfactual Contextual Multi-Armed Bandit: a Real-World Application to Diagnose Apple Diseases—0
CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation—0
CRAB Reader: A Tool for Analysis and Visualization of Argumentative Zones in Scientific Literature—0
Show:102550
← PrevPage 121 of 123Next →

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