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.
Robot Design With Neural Networks, MILP Solvers and Active Learning
Exploiting Context for Robustness to Label Noise in Active Learning
DEAL: Difficulty-aware Active Learning for Semantic Segmentation
ALdataset: a benchmark for pool-based active learning
Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings
Identifying Wrongly Predicted Samples: A Method for Active Learning
Meta-Active Learning for Node Response Prediction in Graphs
Pre-trained Language Model Based Active Learning for Sentence Matching
The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain
Active learning with RESSPECT: Resource allocation for extragalactic astronomical transients
Deep Active Learning for Joint Classification & Segmentation with Weak Annotator
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks
Model Exploration with Cost-Aware Learning
DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
OLALA: Object-Level Active Learning for Efficient Document Layout Annotation
MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps
SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup
Data-efficient Online Classification with Siamese Networks and Active Learning
Neural Bootstrapper
HUMAN: Hierarchical Universal Modular ANnotator
Gaussian Process Molecule Property Prediction with FlowMO
Active Learning for Bayesian 3D Hand Pose Estimation
Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
Experimental Design for Overparameterized Learning with Application to Single Shot Deep Active Learning
Multi-task Causal Learning with Gaussian Processes
Online Learning of Non-Markovian Reward Models
ALICE: Active Learning with Contrastive Natural Language Explanations
Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks
DISPATCH: Design Space Exploration of Cyber-Physical Systems
Active Learning for Product Type Ontology Enhancement in E-commerce
Mean-Variance Analysis in Bayesian Optimization under Uncertainty
Synbols: Probing Learning Algorithms with Synthetic Datasets
Beyond Accuracy: ROI-driven Data Analytics of Empirical Data
On Computability, Learnability and Extractability of Finite State Machines from Recurrent Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.