I remember when I learnt a few chords on the piano, then subjected anyone who would listen to my attempts at making music.

‘That’s nice’, they’d say, patting me on the head as everyone made a beeline for the nearest exit.

We’ll give Google Brain’s Project Magenta a little more credit though, because the AI machine has just composed its first 90-second melody after being fed just four musical notes to start.

Go on, give it a listen:

Then TheNextWeb with why we should be impressed:

It’s the result of Google’s Project Magenta, which aims to use machine learning to create music and art, and bridge the communities between those interests with coders and researchers. Magenta is built on top of its TensorFlow system, and you can find the open-sourced materials through its Github.

The team says the challenge is not to just get Google machines to create art, but to be able to tell stories from it. After all, that’s what artists do with their crafts: to compose a narrative into their work then share them with the world.

If all that has made you a little cross-eyed then let’s chat in in layman’s terms – below from HotAir:

While the music is, at least to my ear, pretty dreadful… it is, without question, music. It’s not music that was written by a human being and then reproduced or enhanced by the algorithm. This is a new song. I’m sure they instructed the program on how different notes fit together to make chords and which ones relate to each other in ways humans generally consider harmonious, but there’s only so much you can do to describe “art” to something that’s never experienced it. They gave it four notes to start off and it began building out from there and wrote an actual song. It’s not just repeating those four notes, either. It takes off into new areas and builds a melody, a harmony and a beat.

True, this little jingle isn’t going to knock some pop singer off the top of the charts, but given enough time maybe we’ll see AI composing beats used by these artists on their albums.

[sources:thenextweb&hotair]