Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression

Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression

Autoencoders are feedforwardneural networks which attempt to reconstruct the input data at the output layer. Since the hidden layer in the autoencoders is smaller than the input layer, the dimensionality of input data is reduced to a smaller dimensional code space at the hidden layer. The reduced co...

Full description

Saved in:
Bibliographic Details
Main Author: Tan, Chun Chet
Format: Thesis
Published: 2008
Subjects:
QA76.75-76.765 Computer software
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-mmu-ep.1563
record_format uketd_dc
spelling my-mmu-ep.15632010-09-23T06:46:42Z Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression 2008-05 Tan, Chun Chet QA76.75-76.765 Computer software Autoencoders are feedforwardneural networks which attempt to reconstruct the input data at the output layer. Since the hidden layer in the autoencoders is smaller than the input layer, the dimensionality of input data is reduced to a smaller dimensional code space at the hidden layer. The reduced codes from the hidden layer are then reconstructed back into the original data at the output layer. Like Principal Component Analysis (PCA), the autoencoders can give mappings in both directions between the data and the codes. 2008-05 Thesis http://shdl.mmu.edu.my/1563/ http://myto.perpun.net.my/metoalogin/logina.php masters Multimedia University Research Library
institution Multimedia University
collection MMU Institutional Repository
topic QA76.75-76.765 Computer software
spellingShingle QA76.75-76.765 Computer software
Tan, Chun Chet
Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression
description Autoencoders are feedforwardneural networks which attempt to reconstruct the input data at the output layer. Since the hidden layer in the autoencoders is smaller than the input layer, the dimensionality of input data is reduced to a smaller dimensional code space at the hidden layer. The reduced codes from the hidden layer are then reconstructed back into the original data at the output layer. Like Principal Component Analysis (PCA), the autoencoders can give mappings in both directions between the data and the codes.
format Thesis
qualification_level Master's degree
author Tan, Chun Chet
author_facet Tan, Chun Chet
author_sort Tan, Chun Chet
title Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression
title_short Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression
title_full Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression
title_fullStr Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression
title_full_unstemmed Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression
title_sort autoencoder neural networks: a performance study based on image recognition, reconstruction and compression
granting_institution Multimedia University
granting_department Research Library
publishDate 2008
_version_ 1747829402068058112

Similar Items