Classification of music tracks based on machine learning
keywords MACHINE LEARNING, NEURAL NETWORKS, EMBEDDED SYSTEMS, C++ PROGRAMMING, NUMERICAL ANALYSIS,
Reference persons MASSIMO PONCINO
Research Groups GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA
Thesis type MASTER THESIS
Description Most classification task using machine learning are related to image (and thus video) classification. Little work is available on the classification of audio tracks, and it is especially related to the identification of the musical preferences of a user based on choices in the history of listened music.
Objective of the thesis is the classification of musical tracks to determine their chance of success; the classification will be based on machine learning but the choice type of technique (simpler classifier or neural networks) will be decided as a part of the project. The design of the training phase will be an important part of the process.
Required skills C/C++ programming, embedded systems programming
Deadline 01/05/2019 PROPONI LA TUA CANDIDATURA