Image Classification Algorithm Using Unsupervised Deep learning and Self-Organizing Map
- Year of publication
- Jong Hyuk Lee, Ki Hoon Kwon, Jong Pil Yun, Min Young Kim
- Institute of Control, Robotics and Systems 2018
In recently, supervised learning is one of the most used artificial intelligence systems in the factory. But It takes a lot of time and manpower to classify each type of defect. In this paper, propose a clustering method using feature combining Autoencoder and Self-Organizing Map techniques. The experimental results show 60% clustering accuracy for MNIST dataset and 90% accuracy for fashion MNIST dataset.