Journal
NEUROCOMPUTING
Volume 184, Issue -, Pages 232-242Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2015.08.104
Keywords
Auto-encoder; Dimensionality reduction; Visualization; Intrinsic dimensionality; Dimensionality-accuracy
Categories
Funding
- National Natural Science Foundation of China [61472103]
- [61133003]
Ask authors/readers for more resources
Auto-encoder a tricky three-layered neural network, known as auto-association before, constructs the building block of deep learning, which has been demonstrated to achieve good performance in various domains. In this paper, we try to investigate the dimensionality reduction ability of auto-encoder, and see if it has some kind of good property that might accumulate when being stacked and thus contribute to the success of deep learning. Based on the above idea, this paper starts from auto-encoder and focuses on its ability to reduce the dimensionality, trying to understand the difference between auto-encoder and state-of-the-art dimensionality reduction methods. Experiments are conducted both on the synthesized data for an intuitive understanding of the method, mainly on two and three-dimensional spaces for better visualization, and on some real datasets, including MNIST and Olivetti face datasets. The results show that auto-encoder can indeed learn something different from other methods. Besides, we preliminarily investigate the influence of the number of hidden layer nodes on the performance of auto-encoder and its possible relation with the intrinsic dimensionality of input data. (C) 2015 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available