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.
Effective Version Space Reduction for Convolutional Neural Networks
Fair Active Learning
Boosting Active Learning for Speech Recognition with Noisy Pseudo-labeled Samples
Sequential Graph Convolutional Network for Active Learning
Active Learning for Nonlinear System Identification with Guarantees
On the Robustness of Active Learning
GPIRT: A Gaussian Process Model for Item Response Theory
Bayesian active learning for production, a systematic study and a reusable library
Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms
High-contrast "gaudy" images improve the training of deep neural network models of visual cortex
Fourier Sparse Leverage Scores and Approximate Kernel Learning
On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning
Active Invariant Causal Prediction: Experiment Selection through Stability
Dialog Policy Learning for Joint Clarification and Active Learning Queries
Learning compositional models of robot skills for task and motion planning
Sophisticated Inference
How useful is Active Learning for Image-based Plant Phenotyping?
Attribute-Efficient Learning of Halfspaces with Malicious Noise: Near-Optimal Label Complexity and Noise Tolerance
Aspect-based Sentiment Analysis of Scientific Reviews
Committee neural network potentials control generalization errors and enable active learning
Toward Optimal Probabilistic Active Learning Using a Bayesian Approach
A2-LINK: Recognizing Disguised Faces via Active Learning and Adversarial Noise based Inter-Domain Knowledge
Adaptive quadrature schemes for Bayesian inference via active learning
MM-KTD: Multiple Model Kalman Temporal Differences for Reinforcement Learning
Machine learning methods to detect money laundering in the Bitcoin blockchain in the presence of label scarcity
JointMap: Joint Query Intent Understanding For Modeling Intent Hierarchies in E-commerce Search
Active Fuzzing for Testing and Securing Cyber-Physical Systems
Fuzziness-based Spatial-Spectral Class Discriminant Information Preserving Active Learning for Hyperspectral Image Classification
Active Imitation Learning with Noisy Guidance
Minimizing Supervision in Multi-label Categorization
Discriminative Active Learning for Domain Adaptation
Active Learning for Skewed Data Sets
Batch Decorrelation for Active Metric Learning
Stopping criterion for active learning based on deterministic generalization bounds
VirAAL: Virtual Adversarial Active Learning For NLU
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.