Show simple item record

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorThierens, D.
dc.contributor.authorJanssen, R.R.P.
dc.date.accessioned2020-07-30T18:00:31Z
dc.date.available2020-07-30T18:00:31Z
dc.date.issued2020
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/36435
dc.description.abstractFunctionally equivalent multi-layer perceptron networks (MLPs) can be written in many different forms. This presents difficulty when trying to recombine these networks using the crossover operator. This thesis aims at finding a method to identify similar neurons in different MLPs by their parameters. This allows for defining crossover operators that do not depend on the forms in which different networks are written. Two new crossover operators are presented that use similarity between the parameters of different neurons to facilitate a non-disruptive crossover. These crossover operators have been found to be relatively non-disruptive compared to uniform and one-point crossover.
dc.description.sponsorshipUtrecht University
dc.format.extent944607
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.titleA Non-disruptive Crossover Operator for Multi-layer Perceptron Networks using Parametric Similarity
dc.type.contentMaster Thesis
dc.rights.accessrightsOpen Access
dc.subject.keywordsNeural Networks; Multi-layer Perceptron; Crossover; Genetic Algorithms
dc.subject.courseuuArtificial Intelligence


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record