Recomendador h?brido musical basado en contenido e informaci?n social
- Authors
- Chiliguano Torres, Paulo Esteban
- Format
- DoctoralThesis
- Status
- publishedVersion
- Description
There is a vast range of Internet resources available today, including songs, albums, playlists or podcasts, that a user cannot discover if there is not a tool to lter the items that the user might consider relevant. Several recommendation techniques has been developed since the internet explosion to achieve this ltering task. In an attempt to recommend relevant song to users, we propose an hybrid recommender that considers real-world users information and high-level representation for audio data. We use a deep learning technique, convolutional deep neural network, to represent the audio data in an abstract level. As our main contribution, we investigate a stateof-the-art technique, estimation of distribution algorithm, to capture the listening behaviour of an individual from the features of the songs that are interesting to the user. The designed hybrid music recommender outperform the predictions compared with a traditional content-based recommender.
El presente estudio propone un sistema de recomendaci?n h?brido considerando informaci?n real de usuarios y representaci?n de alto nivel de informaci?n de audio. Se emplean t?cnicas de aprendizaje autom?tico para la representaci?n abstracta de audio. Como contribuci?n principal, se investiga la estimaci?n de algoritmos de distribuci?n para capturar el comportamiento de los usuarios acorde al inter?s musical de los mismos.
- Publication Year
- 2015
- Language
- eng
- Topic
- APRENDIZAJE AUTOM?TICO
SISTEMAS DE RECOMENDACI?N
REDES NEURONALES
ALGORITMOS DE DISTRIBUCI?N
- Repository
- Repositorio SENESCYT
- Rights
- openAccess
- License