News for hackers. Stuff that matters.
Re:Classical music generation with recurrent neural networks by avodonosov on Saturday August 08, 2015 @10:17PM (#10029299)
Or more illustrative analogy: if it was generating text instead of music, and produced a sequence of words - some unfinished sentences, or maybe even complete sentences, maybe even sharing subjects (names) sometimes between sentences. But the whole text does not deliver any story. But you say: "maybe it's a story, where all these words follow each other". Well, maybe, for someone. Maybe it is anvant-garde poetry.

But for me this opus has no real meaning.

Re:Classical music generation with recurrent neural networks by eggy on Sunday August 09, 2015 @12:23AM (#10029488)
Sort of like 'Finnegan's Wake' :)
Re:Classical music generation with recurrent neural networks by marquis on Sunday August 09, 2015 @03:28AM (#10029777)
Finnegan's Wake is packed-full of self-referential meta-data and has a highly coherent structure.

In this sense, it's relevant to the discussion because it may appear to have been created by Markov chains whereas in fact it's intelligently molded and makes (more and more interesting) sense from the many perspectives you start to have as you spend your life with it.

Excellent project here, which even from reading the first page you'll have an a-ha moment: http://www.wakeinprogress.com/2010/10/introduction-to-charac...