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.
Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainability
Active Learning for Massively Parallel Translation of Constrained Text into Low Resource Languages
Neural Predictive Monitoring under Partial Observability
Towards Visual Explainable Active Learning for Zero-Shot Classification
Deep Active Learning for Text Classification with Diverse Interpretations
Jasmine: A New Active Learning Approach to Combat Cybercrime
Reinforcement Learning Approach to Active Learning for Image Classification
Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems
Active Learning for Saddle Point Calculation
Probabilistic Active Learning for Active Class Selection
Reducing Annotating Load: Active Learning with Synthetic Images in Surgical Instrument Segmentation
Active Learning of Driving Scenario Trajectories
Self-supervised optimization of random material microstructures in the small-data regime
Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization
When Deep Learners Change Their Mind: Learning Dynamics for Active Learning
Active Learning in Gaussian Process State Space Model
Semi-Supervised Active Learning with Temporal Output Discrepancy
Batch Active Learning at Scale
Robust and Active Learning for Deep Neural Network Regression
Self-learning Emulators and Eigenvector Continuation
Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
Restless Bandits with Many Arms: Beating the Central Limit Theorem
MCDAL: Maximum Classifier Discrepancy for Active Learning
Robust Adaptive Submodular Maximization
Active Learning in Incomplete Label Multiple Instance Multiple Label Learning
Small-Text: Active Learning for Text Classification in Python
Offline Preference-Based Apprenticeship Learning
Fully Automated Machine Learning Pipeline for Echocardiogram Segmentation
The Application of Active Query K-Means in Text Classification
Active learning for imbalanced data under cold start
Seeing and Believing: Evaluating the Trustworthiness of Twitter Users
Zero-Round Active Learning
Improving Cooperative Game Theory-based Data Valuation via Data Utility Learning
Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.