Reconstruction of handwritten digit images using autoencoder neural networks

This paper compares the performances of three types of autoencoder neural networks, namely, the traditional autoencoder with restricted Boltzmann machine (RBM), the stacked autoencoder without RBM and the stacked autoencoder with RBM based on the efficiency for reconstruction of handwritten digit im...

Full description

Saved in:
Bibliographic Details
Published in:2008 Canadian Conference on Electrical and Computer Engineering pp. 000465 - 000470
Main Authors: Tan, C.C., Eswaran, C.
Format: Conference Proceeding
Language:English
Published: IEEE 01.05.2008
Subjects:
Autoencoder
Backpropagation
Decoding
dimensionality reduction
Distributed computing
Feedforward neural networks
Image reconstruction
Information technology
Multi-layer neural network
Multimedia computing
neural network
Neural networks
Principal component analysis
Restricted Boltzmann Machine
ISBN:9781424416424, 1424416426
ISSN:0840-7789
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper compares the performances of three types of autoencoder neural networks, namely, the traditional autoencoder with restricted Boltzmann machine (RBM), the stacked autoencoder without RBM and the stacked autoencoder with RBM based on the efficiency for reconstruction of handwritten digit images. Experiments are performed to determine the reconstruction error in all the three cases using the same architecture configuration and training algorithm. The results show that the RBM stacked autoencoder gives better performance in terms of the reconstruction error compared to the other two architectures. We also show that all the architectures outperform PCA in terms of the reconstruction error.
ISBN:9781424416424
1424416426
ISSN:0840-7789
DOI:10.1109/CCECE.2008.4564577