Institutional-Repository, University of Moratuwa.  

Towards a theoretical basis for modelling of hidden layer architecture in artificial neural networks

Show simple item record

dc.contributor.author Wagarachchi, NM
dc.contributor.author Karunananda, AS
dc.date.accessioned 2018-06-14T01:22:28Z
dc.date.available 2018-06-14T01:22:28Z
dc.identifier.uri http://dl.lib.mrt.ac.lk/handle/123/13187
dc.description.abstract Artificial neural networks (ANNs) arc mathematical and computational models that arc inspired by the biological neural systems. Just like biological neural networks become experts by learning from the surrounding, ANNs also have the ability to be experts in the particular area by training the network. Despite of their many advantages, there are some unsolved problems in applying artificial neural networks. Determine the most efficient architecture for the given task is identified as one of those major issues. This paper provides a pruning algorithm based on the baekpropagalion training algorithm to obtain the optimal solution of ANN. The pruning is done according to the synaptic pruning in biological neural system. Experiments were done with some well known problems in machine learning and artificial neural networks and results show that the new model performs better than the initial network in training data sets. en_US
dc.language.iso en en_US
dc.subject artificial neural netowrks; backpropagation; delta values; hidden layer architecture; en_US
dc.title Towards a theoretical basis for modelling of hidden layer architecture in artificial neural networks en_US
dc.type Conference-Abstract en_US
dc.identifier.faculty IT en_US
dc.identifier.department Department of Computational Mathematics en_US
dc.identifier.year 2014 en_US
dc.identifier.conference 2nd International Conference on Advances in Computing, Electronics and Communication - (ACEC - 2014) en_US
dc.identifier.place Zurich en_US
dc.identifier.pgnos pp. 47 - 52 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record