Citation

Tan, Chun Chet (2008) Autoencoder Neural Networks: A Performance Study Based On Image Recognition, Reconstruction And Compression. Masters thesis, Multimedia University.

Full text not available from this repository.

Abstract

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.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	23 Sep 2010 06:46
Last Modified:	23 Sep 2010 06:46
URII:	http://shdl.mmu.edu.my/id/eprint/1563

Downloads

Edit (login required)