Show simple item record

dc.contributor.authorRamli, Irwan
dc.contributor.supervisorCesar Ortega-Sanchezen_US

Hierarchical Concatenation Networks (HCN) are inspired by the way humans recognize patterns; i.e. by concatenating small features. In HCNs patterns are split into small parts, and then concatenated and activated in the network’s layers. The research in this thesis investigated and explored feature extraction methods, similarity measures, and classification using HCNs. Results indicate that HCNs can be used in automatic pattern recognition systems with better performance rate on the lower layer than the top layer.

dc.publisherCurtin Universityen_US
dc.titleA Study of Hierarchical Concatenation Networks in the Area of Pattern Recognitionen_US
curtin.departmentDepartment of Electrical & Computer Engineeringen_US
curtin.accessStatusOpen accessen_US
curtin.facultyScience and Engineeringen_US

Files in this item


This item appears in the following Collection(s)

Show simple item record