view poster/sections/conc.tex @ 47:b0186d4a4496 tip

Move 7Digital dataset to Downloads

\section{Conclusions}

\begin{itemize}
\item We investigated and considered EDA for modelling users' listening behaviour in terms of probabilities of music genres from the songs in they have listened.
\item We found the CNN achieve similar results to long-established music genre classifier approaches in music information retrieval field.
\item The results show that using a discrete values in EDA can outperform a single content-based recommender.
\item We aim to build on this work by implementing unsupervised deep learning networks and an online evaluation interface.
\end{itemize}