Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps

In this thesis, discussions are made about several questions in music informatics through the design and development of a system to generate melodies and the system utilizes the Hierarchical Self-Organizing Map (HSOM), an unsupervised neural network model that is commonly used in tasks of data visua...

Full description

Saved in:

Bibliographic Details
Main Author:	Hean, Edwin Law Hui
Format:	Thesis
Published:	2010
Subjects:	Q Science (General)
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-mmu-ep.3491
record_format	uketd_dc
spelling	my-mmu-ep.34912012-04-12T03:30:37Z Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps 2010-01 Hean, Edwin Law Hui Q Science (General) In this thesis, discussions are made about several questions in music informatics through the design and development of a system to generate melodies and the system utilizes the Hierarchical Self-Organizing Map (HSOM), an unsupervised neural network model that is commonly used in tasks of data visualization and clustering, as a memory store of melodies. More specifically, the thesis tackles the problem of Melody Generation which is still a wide open research area in music informatics. Various methods that make use of techniques like machine learning, encoded rules, evolutionary computation, statistical analysis and so on have been proposed over the years and this thesis borrows ideas from various research to formulate a system inspired by the Memory Prediction Framework and built using the HSOM. 2010-01 Thesis http://shdl.mmu.edu.my/3491/ http://vlib.mmu.edu.my/diglib/login/dlusr/login.php masters University of Multimedia Research Library
institution	Multimedia University
collection	MMU Institutional Repository
topic	Q Science (General)
spellingShingle	Q Science (General) Hean, Edwin Law Hui Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps
description	In this thesis, discussions are made about several questions in music informatics through the design and development of a system to generate melodies and the system utilizes the Hierarchical Self-Organizing Map (HSOM), an unsupervised neural network model that is commonly used in tasks of data visualization and clustering, as a memory store of melodies. More specifically, the thesis tackles the problem of Melody Generation which is still a wide open research area in music informatics. Various methods that make use of techniques like machine learning, encoded rules, evolutionary computation, statistical analysis and so on have been proposed over the years and this thesis borrows ideas from various research to formulate a system inspired by the Memory Prediction Framework and built using the HSOM.
format	Thesis
qualification_level	Master's degree
author	Hean, Edwin Law Hui
author_facet	Hean, Edwin Law Hui
author_sort	Hean, Edwin Law Hui
title	Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps
title_short	Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps
title_full	Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps
title_fullStr	Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps
title_full_unstemmed	Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps
title_sort	machine learning of melodies through hierarchical self-organizing maps
granting_institution	University of Multimedia
granting_department	Research Library
publishDate	2010
_version_	1747829508678877184

Machine Learning Of Melodies Through Hierarchical Self-Organizing Maps

Similar Items