Change search
ReferencesLink to record
Permanent link

Direct link
A study on the similarities of Deep Belief Networks and Stacked Autoencoders
KTH, School of Computer Science and Communication (CSC).ORCID iD: 0000-0001-6064-5634
2015 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Restricted Boltzmann Machines (RBMs) and autoencoders have been used - in several variants - for similar tasks, such as reducing dimensionality or extracting features from signals. Even though their structures are quite similar, they rely on different training theories. Lately, they have been largely used as building blocks in deep learning architectures that are called deep belief networks (instead of stacked RBMs) and stacked autoencoders.

In light of this, the student has worked on this thesis with the aim to understand the extent of the similarities and the overall pros and cons of using either RBMs, autoencoders or denoising autoencoders in deep networks. Important characteristics are tested, such as the robustness to noise, the influence on training of the availability of data and the tendency to overtrain. The author has then dedicated part of the thesis to study how the three deep networks in exam form their deep internal representations and how similar these can be to each other. In result of this, a novel approach for the evaluation of internal representations is presented with the name of F-Mapping. Results are reported and discussed.

Place, publisher, year, edition, pages
2015. , 70 p.
Keyword [en]
Deep Learning, Restricted Boltzmann Machine, Stacked Autoencoder, Autoencoder, Depp Belief Network, Machine Learning, Computer Science, F-Mapping
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
URN: urn:nbn:se:kth:diva-174341OAI: diva2:859006
Educational program
Master of Science - Machine Learning
Available from: 2015-10-05 Created: 2015-10-05 Last updated: 2015-11-25Bibliographically approved

Open Access in DiVA

fulltext(6396 kB)479 downloads
File information
File name FULLTEXT01.pdfFile size 6396 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
de Giorgio, Andrea
By organisation
School of Computer Science and Communication (CSC)
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 479 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 162 hits
ReferencesLink to record
Permanent link

Direct link