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.
Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study
Batch Active Learning Using Determinantal Point Processes
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
Deep Active Learning for Anchor User Prediction
A sparse annotation strategy based on attention-guided active learning for 3D medical image segmentation
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
RadGrad: Active learning with loss gradients
Bounded Expectation of Label Assignment: Dataset Annotation by Supervised Splitting with Bias-Reduction Techniques
Active Generative Adversarial Network for Image Classification
Low-resource Deep Entity Resolution with Transfer and Active Learning
Online Active Learning of Reject Option Classifiers
Non-Parametric Calibration for Classification
Evaluation of Seed Set Selection Approaches and Active Learning Strategies in Predictive Coding
Self-Supervised Exploration via Disagreement
Human-Machine Collaboration for Fast Land Cover Mapping
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Preference-based Interactive Multi-Document Summarisation
Context-driven Active and Incremental Activity Recognition
Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approach
Active Deep Decoding of Linear Codes
Diameter-based Interactive Structure Discovery
Bayesian Active Learning With Abstention Feedbacks
Reliable training and estimation of variance networks
Active Learning for Binary Classification with Abstention
Minimum-Margin Active Learning
ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition
Learning by Active Nonlinear Diffusion
Understanding Goal-Oriented Active Learning via Influence Functions
Training Data Subset Search with Ensemble Active Learning
MaxiMin Active Learning in Overparameterized Model Classes}
The Label Complexity of Active Learning from Observational Data
Correlation Clustering with Adaptive Similarity Queries
A framework for the extraction of Deep Neural Networks by leveraging public data
Dual Active Sampling on Batch-Incremental Active Learning
Constraining the Parameters of High-Dimensional Models with Active Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.