Papers with Code 아카이브
Active Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 7
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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
HeBERT & HebEMO: a Hebrew BERT Model and a Tool for Polarity Analysis and Emotion Recognition
FOIT: Fast Online Instance Transfer for Improved EEG Emotion Recognition
A Simple yet Brisk and Efficient Active Learning Platform for Text Classification
Exponential Savings in Agnostic Active Learning through Abstention
Teaching Digital Signal Processing by Partial Flipping, Active Learning and Visualization
Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection
Wisdom of the Contexts: Active Ensemble Learning for Contextual Anomaly Detection
Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
On Statistical Bias In Active Learning: How and When To Fix It
Adversarial Vulnerability of Active Transfer Learning
Online Body Schema Adaptation through Cost-Sensitive Active Learning
A Receding Horizon Approach for Simultaneous Active Learning and Control using Gaussian Processes
Safe Learning and Optimization Techniques: Towards a Survey of the State of the Art
DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation
Active Hybrid Classification
Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates
Autonomous synthesis of metastable materials
Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach
Adaptive Remote Sensing Image Attribute Learning for Active Object Detection
Diverse Complexity Measures for Dataset Curation in Self-driving
Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing
Improved active output selection strategy for noisy environments
PowerEvaluationBALD: Efficient Evaluation-Oriented Deep (Bayesian) Active Learning with Stochastic Acquisition Functions
Deep Diffusion Processes for Active Learning of Hyperspectral Images
Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation
Active learning for object detection in high-resolution satellite images
Application of an automated machine learning-genetic algorithm (AutoML-GA) coupled with computational fluid dynamics simulations for rapid engine design optimization
Stochastic Optimization for Vaccine and Testing Kit Allocation for the COVID-19 Pandemic
Active Learning Under Malicious Mislabeling and Poisoning Attacks
Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms
From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach
Whom to Test? Active Sampling Strategies for Managing COVID-19
An Active Learning Method for Diabetic Retinopathy Classification with Uncertainty Quantification
Self-supervised self-supervision by combining deep learning and probabilistic logic
Active Deep Learning on Entity Resolution by Risk Sampling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.