view Report/chiliguano_msc_finalproject.toc @ 25:fafc0b249a73

Final code

\contentsline {chapter}{\numberline {1}Introduction}{1}{chapter.1}
\contentsline {section}{\numberline {1.1}Outline of the thesis}{2}{section.1.1}
\contentsline {chapter}{\numberline {2}Background}{4}{chapter.2}
\contentsline {section}{\numberline {2.1}Online Social Networks}{5}{section.2.1}
\contentsline {subsection}{\numberline {2.1.1}Last.fm}{5}{subsection.2.1.1}
\contentsline {section}{\numberline {2.2}Music services platforms}{6}{section.2.2}
\contentsline {subsection}{\numberline {2.2.1}Echonest}{6}{subsection.2.2.1}
\contentsline {subsection}{\numberline {2.2.2}7Digital}{6}{subsection.2.2.2}
\contentsline {section}{\numberline {2.3}Recommender Systems}{6}{section.2.3}
\contentsline {subsection}{\numberline {2.3.1}Collaborative filtering}{6}{subsection.2.3.1}
\contentsline {subsection}{\numberline {2.3.2}Content-based methods}{7}{subsection.2.3.2}
\contentsline {section}{\numberline {2.4}Hybrid recommender methods}{7}{section.2.4}
\contentsline {section}{\numberline {2.5}Music Information Retrieval}{7}{section.2.5}
\contentsline {subsection}{\numberline {2.5.1}Musical genre classification}{7}{subsection.2.5.1}
\contentsline {subsection}{\numberline {2.5.2}Deep Learning}{8}{subsection.2.5.2}
\contentsline {subsection}{\numberline {2.5.3}Convolutional Neural Networks}{8}{subsection.2.5.3}
\contentsline {section}{\numberline {2.6}Estimation of Distribution Algorithms}{9}{section.2.6}
\contentsline {chapter}{\numberline {3}Methodology}{10}{chapter.3}
\contentsline {section}{\numberline {3.1}Data collection}{10}{section.3.1}
\contentsline {subsection}{\numberline {3.1.1}Taste Profile subset cleaning}{11}{subsection.3.1.1}
\contentsline {subsection}{\numberline {3.1.2}Audio clips retrieval}{11}{subsection.3.1.2}
\contentsline {subsection}{\numberline {3.1.3}Intermediate time-frequency representation for audio signals}{12}{subsection.3.1.3}
\contentsline {section}{\numberline {3.2}Algorithms}{12}{section.3.2}
\contentsline {subsection}{\numberline {3.2.1}CNN architecture}{12}{subsection.3.2.1}
\contentsline {subsubsection}{Genre classification}{13}{section*.2}
\contentsline {subsection}{\numberline {3.2.2}Continuous Bayesian EDA}{13}{subsection.3.2.2}
\contentsline {subsection}{\numberline {3.2.3}EDA-based hybrid recommender}{13}{subsection.3.2.3}
\contentsline {chapter}{\numberline {4}Experiments}{14}{chapter.4}
\contentsline {section}{\numberline {4.1}Evaluation for recommender systems}{14}{section.4.1}
\contentsline {subsection}{\numberline {4.1.1}Types of experiments}{14}{subsection.4.1.1}
\contentsline {section}{\numberline {4.2}Evaluation method}{16}{section.4.2}
\contentsline {subsection}{\numberline {4.2.1}Dataset description}{16}{subsection.4.2.1}
\contentsline {subsection}{\numberline {4.2.2}Evaluation measures}{16}{subsection.4.2.2}
\contentsline {chapter}{\numberline {5}Results}{17}{chapter.5}
\contentsline {chapter}{\numberline {6}Conclusion}{18}{chapter.6}
\contentsline {section}{\numberline {6.1}Future work}{18}{section.6.1}