A Study of Hierarchical Concatenation Networks in the Area of Pattern Recognition
MetadataShow full item record
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.
Showing items related by title, author, creator and subject.
Mucina, Ladislav; van Tongeren, O. (1989)Two sets comprising 1419 and 1350 phytosociological relevrs of ruderal vegetation classified into 9 and 7 orders, respectively, from an area in the Podunajskh nizina Lowland, western Slovakia were ordinated using ...
Duong, Thi V. T. (2008)Modeling patterns in temporal data has arisen as an important problem in engineering and science. This has led to the popularity of several dynamic models, in particular the renowned hidden Markov model (HMM) [Rabiner, ...
Molecular phylogenetics of geographically restricted Acropora species: Implications for threatened species conservationRichards, Zoe; Miller, D.; Wallace, C. (2013)To better understand the underlying causes of rarity and extinction risk in Acropora (staghorn coral), we contrast the minimum divergence ages and nucleotide diversity of an array of species with different range sizes and ...