Unsupervised Image Classification Using Multi-Autoencoder and K-means++

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...

Full description

Bibliographic Details
Main Authors: Shingo Mabu, Kyoichiro Kobayashi, Masanao Obayashi, Takashi Kuremoto
Format: Article
Language:English
Published: Atlantis Press 2018-06-01
Series:Journal of Robotics, Networking and Artificial Life (JRNAL)
Subjects:
Online Access:https://www.atlantis-press.com/article/25896478/view