Abstract | ||
---|---|---|
As a robust and heuristic technique in machine learning, active learning has been established as an effective method for addressing large volumes of unlabeled data; it interactively queries users (or certain information sources) to obtain desired outputs at new data points. With regard to deep learning techniques (e.g., CNN) and their applications (e.g., image classification), labeling work is of great significance as training processes for obtaining parameters in neural networks which requires abundant labeled samples. Although a few active learning algorithms have been proposed for devising certain straightforward sampling strategies (e.g., density, similarity, uncertainty, and label-based measure) for deep learning algorithms, these employ onefold sampling strategies and do not consider the relationship among multiple sampling strategies. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.knosys.2019.02.013 | Knowledge-Based Systems |
Keywords | Field | DocType |
Deep neural network,Active learning,Multi-criteria,Image classification | Data point,Data mining,Heuristic,Active learning,MNIST database,Computer science,Sampling (statistics),Artificial intelligence,Deep learning,Artificial neural network,Contextual image classification,Machine learning | Journal |
Volume | ISSN | Citations |
172 | 0950-7051 | 4 |
PageRank | References | Authors |
0.39 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jin Yuan | 1 | 18 | 3.65 |
Xingxing Hou | 2 | 4 | 0.39 |
Yaoqiang Xiao | 3 | 4 | 0.72 |
Da Cao | 4 | 74 | 4.79 |
Weili Guan | 5 | 43 | 10.84 |
Liqiang Nie | 6 | 2975 | 131.85 |