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

Composing Music with LSTM Recurrent Networks – Blues Improvisation (2002)

people.idsia.ch

Post reply on HN
Print view View original

11–14 of 14 posts

Re: Composing Music with LSTM Recurrent Networks – Blues Improvisation (2002)

#11

Post by douglaseck »

gwern wrote: post #7
SCHiM wrote: post #3

Interesting, but it feels like the music is forever stuck in an into of some kind. I never quite get the feeling that it's building towards something.

Think that may be by design: > The goal of these experiments were to see if LSTM could learn a fixed chord structure while in parallel learning elements of a varying melody structure. It was easier to stick with a basic melody. Note that every 12-bar segment is unique; however, because only one or two bars are changed at a time, you may have to listen for a while to hear differences. We are currently working on a muc…

"We are currently working on a much more interesting set of training melodies and chords". More like "my postdoc ended in Switzerland and I started a faculty job at University of Montreal (LISA lab) and never had time to get back to LSTM and music composition. Sigh.

Re: Composing Music with LSTM Recurrent Networks – Blues Improvisation (2002)

#12

Post by helical »

Smerity wrote: post #5
albertzeyer wrote: post #4

This is from 2002, right?

It is indeed - I'd suggest the title is modified to add year as it provides context for how long LSTMs have been established before their recent popularity boom. https://scholar.google.com/scholar?hl=en&q=A+First+Look+at+M...

Unfortunately, I can no longer modify the title.

Re: Composing Music with LSTM Recurrent Networks – Blues Improvisation (2002)

#13

Post by cwhy »

douglaseck wrote: post #9

Author ( http://research.google.com/pubs/author39086.html ) of the paper here. I'm amused this is on Hacker News. The goal was to learn very long-timescale limit cycle behavior in a recurrent neural network. The chord changes are separated by many intervening melodic events (notes). As it turns out, even LSTM is pretty fragile when it comes to this. One problem is stability: if the network gets too perturbed, it can…

Hi Douglas, I just finished my college and quite interested in RNNs and fascinated by their capability and potential. Should I go to graduate school to study it or I can play with it as a hobby. Do you have any suggestions?

Re: Composing Music with LSTM Recurrent Networks – Blues Improvisation (2002)

#14

Post by douglaseck »

cwhy wrote: post #13
douglaseck wrote: post #9

Author ( http://research.google.com/pubs/author39086.html ) of the paper here. I'm amused this is on Hacker News. The goal was to learn very long-timescale limit cycle behavior in a recurrent neural network. The chord changes are separated by many intervening melodic events (notes). As it turns out, even LSTM is pretty fragile when it comes to this. One problem is stability: if the network gets too perturbed, it can…

Hi Douglas, I just finished my college and quite interested in RNNs and fascinated by their capability and potential. Should I go to graduate school to study it or I can play with it as a hobby. Do you have any suggestions?

I think you could play around as a hobby. You might try Theano as a place to start (for LSTM: http://deeplearning.net/tutorial/lstm.html). If you become passionate about neural networks you might find yourself in grad school simply because that's a great place for diving in more deeply. It's really really helpful to know machine learning. Andrew Ng's Coursera is a great place to start: https://www.coursera.org/course/ml
Post reply on HN