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.
Active Semi-supervised Transfer Learning (ASTL) for Offline BCI Calibration
Textual Membership Queries
Efficient active learning of sparse halfspaces
Bayesian active learning for choice models with deep Gaussian processes
modAL: A modular active learning framework for Python
Streaming Active Learning Strategies for Real-Life Credit Card Fraud Detection: Assessment and Visualization
Active Learning for Breast Cancer Identification
Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner
Active Learning for Efficient Testing of Student Programs
Derivative free optimization via repeated classification
A Deep Active Survival Analysis Approach for Precision Treatment Recommendations: Application of Prostate Cancer
Active covariance estimation by random sub-sampling of variables
Active Metric Learning for Supervised Classification
Supervising Feature Influence
Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection
Handling Adversarial Concept Drift in Streaming Data
Evaluating Sentence-Level Relevance Feedback for High-Recall Information Retrieval
Structural query-by-committee
Leveraging Crowdsourcing Data For Deep Active Learning - An Application: Learning Intents in Alexa
Dimension-Robust MCMC in Bayesian Inverse Problems
Highly Automated Learning for Improved Active Safety of Vulnerable Road Users
Multi-class Active Learning: A Hybrid Informative and Representative Criterion Inspired Approach
Differentiable Submodular Maximization
Deep Bayesian Active Semi-Supervised Learning
Active model learning and diverse action sampling for task and motion planning
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling
Adversarial Active Learning for Deep Networks: a Margin Based Approach
Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning
Best Arm Identification for Contaminated Bandits
Active Learning with Logged Data
Active Learning with Partial Feedback
Distributional Term Set Expansion
Fast Interactive Image Retrieval using large-scale unlabeled data
Thompson Sampling for Dynamic Pricing
Active, Continual Fine Tuning of Convolutional Neural Networks for Reducing Annotation Efforts
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.