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.
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss
Crowd Sourcing based Active Learning Approach for Parking Sign Recognition
Explore-Exploit: A Framework for Interactive and Online Learning
Learning to Caption Images through a Lifetime by Asking Questions
Are All Training Examples Created Equal? An Empirical Study
Active Learning in Recommendation Systems with Multi-level User Preferences
Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision
The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning
$HS^2$: Active Learning over Hypergraphs
Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence
Robust Active Learning for Electrocardiographic Signal Classification
Computer-Assisted Fraud Detection, From Active Learning to Reward Maximization
Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning
Deep Active Learning with a Neural Architecture Search
Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensembles
Active Learning using Deep Bayesian Networks for Surgical Workflow Analysis
Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization
Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls
Exploring Connections Between Active Learning and Model Extraction
A Bayesian Approach for Sequence Tagging with Crowds
Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
Prediction of Atomization Energy Using Graph Kernel and Active Learning
Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments
Technology Assisted Reviews: Finding the Last Few Relevant Documents by Asking Yes/No Questions to Reviewers
Learning a Set of Interrelated Tasks by Using Sequences of Motor Policies for a Strategic Intrinsically Motivated Learner
Batch Active Preference-Based Learning of Reward Functions
Discovering General-Purpose Active Learning Strategies
Active Learning for New Domains in Natural Language Understanding
Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice
Generative Adversarial Active Learning for Unsupervised Outlier Detection
Target-Independent Active Learning via Distribution-Splitting
An Intelligent Extraversion Analysis Scheme from Crowd Trajectories for Surveillance
A novel active learning framework for classification: using weighted rank aggregation to achieve multiple query criteria
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.