Information Theory for Analyzing Neural Networks
The goal of this thesis was to investigate how information theory could be used to analyze artificial neural networks. For this purpose, two problems, a classification problem and a controller problem were considered. The classification problem was solved with a feedforward neural network trained wi...
Main Author: | Sørngård, Bård |
---|---|
Format: | Others |
Language: | English |
Published: |
Norges teknisk-naturvitenskapelige universitet, Institutt for datateknikk og informasjonsvitenskap
2014
|
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-26773 |
Similar Items
-
Calculations on the possibilities for photoionization-delay studies with circularly polarized light
by: Sörngård, Johan
Published: (2021) -
Neural networks, information theory and knowledge representation
by: Smith, Julian P.
Published: (1996) -
Application of generalized neural network and information theory for chemical process
by: Chun Hsien Lin, et al.
Published: (1999) -
Analyzing Prediction Performance between Wavelet Neural Network and Product-Unit Neural Network
by: Othman, Z., et al.
Published: (2020) -
Applications of Artificial Neural Network and Wavelet Theory to Analyze the Fluctuation of Groundwater Level Before An Earthquake Appears
by: Ci-Yu Liao, et al.
Published: (2005)