title: Learning and Generalisation in Neural Networks with Local Preprocessing
creator: Kutsia, Merab
subject: 530
subject: 530 Physics
description: We study learning and generalisation ability of a specific two-layer feed-forward neural network and compare its properties to that of a simple perceptron. The input patterns are mapped nonlinearly onto a hidden layer, much larger than the input layer, and this mapping is either fixed or may result from   an unsupervised learning process. Such preprocessing of initially uncorrelated random patterns results in the correlated patterns in the hidden layer. The hidden-to-output mapping of the network is performed by a simple perceptron, trained using a supervised learning process. We investigate the effects of the correlations on the learning and generalisation properties as opposed to those of a simple perceptron with uncorrelated patterns. As it turns out, this architecture has some advantages over a simple perceptron.
date: 2007
type: Dissertation
type: info:eu-repo/semantics/doctoralThesis
type: NonPeerReviewed
format: application/pdf
identifier: https://archiv.ub.uni-heidelberg.de/volltextserverhttps://archiv.ub.uni-heidelberg.de/volltextserver/7598/1/Kutsia_PhD.pdf
identifier: DOI:10.11588/heidok.00007598
identifier: urn:nbn:de:bsz:16-opus-75985
identifier:   Kutsia, Merab  (2007) Learning and Generalisation in Neural Networks with Local Preprocessing.  [Dissertation]     
relation: https://archiv.ub.uni-heidelberg.de/volltextserver/7598/
rights: info:eu-repo/semantics/openAccess
rights: http://archiv.ub.uni-heidelberg.de/volltextserver/help/license_urhg.html
language: eng