Mercurial > hg > hybrid-music-recommender-using-content-based-and-social-information
annotate Report/chapter6/conclusions.tex @ 29:b1c54790ed97
Report update
author | Paulo Chiliguano <p.e.chiilguano@se14.qmul.ac.uk> |
---|---|
date | Tue, 01 Sep 2015 11:29:38 +0100 |
parents | a95e656907c3 |
children | eba57dbe56f3 |
rev | line source |
---|---|
p@20 | 1 \chapter{Conclusion} |
p@28 | 2 \label{ch:conclusion} |
p@29 | 3 %``Representations of music directly from the temporal or spectral domain can be very sensitive to small time and frequency deformations''. \parencite{zhang2014deep} |
p@29 | 4 |
p@27 | 5 \section{Future work} |
p@20 | 6 |
p@27 | 7 \begin{itemize} |
p@27 | 8 \item Download more audio data from 7digital catalog. |
p@27 | 9 \item Consider another high-level representation instead of music genres or extend the number of genres. |
p@27 | 10 \item Predict rating values of items from users' neighbourhood to evaluate the performance of our hybrid recommender and compare it with a traditional collaborative filtering baseline. |
p@27 | 11 \item Optimisation of the profile using latent vectors. |
p@27 | 12 \end{itemize} |