Abstract | ||
---|---|---|
Supervised learning algorithms such as deep neural networks have been actively applied to various problems. However, in image classification problem, for example, supervised learning needs a large number of data with correct labels. In fact, the cost of giving correct labels to the training data is large; therefore, this paper proposes an unsupervised image classification system with Multi-Autoencoder and K-means++ and evaluates its performance using benchmark image datasets. |
Year | DOI | Venue |
---|---|---|
2018 | 10.2991/jrnal.2018.5.1.17 | JOURNAL OF ROBOTICS NETWORKING AND ARTIFICIAL LIFE |
Keywords | Field | DocType |
neural network,deep autoencoder,K-means++,clustering | k-means clustering,Autoencoder,Pattern recognition,Computer science,Artificial intelligence,Contextual image classification | Journal |
Volume | Issue | ISSN |
5 | 1 | 2352-6386 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shingo Mabu | 1 | 493 | 77.00 |
Kyoichiro Kobayashi | 2 | 0 | 0.34 |
Masanao Obayashi | 3 | 198 | 26.10 |
Takashi Kuremoto | 4 | 196 | 27.73 |