Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Building a Music Recommender with Deep Learning

mattmurray.net

Post reply on HN
Print view View original

71–74 of 74 posts

Re: Building a Music Recommender with Deep Learning

#71

Post by naushniki »

oscii wrote: post #18

In my opinion, the results are not quite exciting as they might seem like at the first glance. The hip-hop and minimal house classification perform almost randomly (the random classifier would have accuracy of 50%). The claim of music genre subjectivity is not fully appropriate for the categories used in this work: the presented genres are quite distinct, and they have objective differences. Knowing only BMP and rhyt…

I agree that the resulting application is rather primitive. Although it was interesting for me, as someone who just learned the theory behind ML, to see how an ML application is built from front to end. I expect that real world applications would encompass a lot of knowledge, which you normally learn after you developed the first version of the app and started using it. I wonder if there are articles out there, which share ordered and filtered information on that.

Re: Building a Music Recommender with Deep Learning

#72

Post by SanderMak »

flashman wrote: post #26
johnlbevan2 wrote: post #12

Warning: this comment has little to do with the article, beyond being a rant on the approach taken by all recommendation engines I've seen. This an interesting approach, but the objective is similar to most recommendation engines: "Find me something similar to something I like". Sometimes that's a good requirement (e.g. when trying to queue up the next song in a playlist, it's good to have some similarity to the song…

> Popular songs (i.e. if almost everyone has a Beetles album in their playlist, getting "people who bought this also bought" recommendations for anything would list Beetles I've been learning recommendation engines by looking at peoples' Steam games libraries. One feature of the data set is that many, many people own multiple versions of Counter-Strike as well as Team Fortress 2. So "a high number people who bought […

I think 'serendipity' [1] is the most-used term in recommender systems to describe what you mean.

[1] https://books.google.nl/books?id=_AfABAAAQBAJ&pg=PA258&lpg=P...

Re: Building a Music Recommender with Deep Learning

#73

Post by mkorfmann »

rahimnathwani wrote: post #58
dnadler wrote: post #20

Very cool! One minor nitpick -- the author mentions that this is 'completely unsupervised'. It's true that the author didn't need to manually classify the data, but someone did. So, I believe that this is actually supervised learning, as the author is training a classifier on preexisting labels (the genres). I believe that unsupervised learning would not make use of a target variable at all. If the network architectu…

You're correct of course. But it's cool that you can learn a useful embeddings (in this case into a 128-dimensional space) with only relative few (in this case 9) binary labels.

I'd love to see an analysis of what exactly these embeddings represent concerning the musical features of a sound snippet.
Post reply on HN