4.1 • 11.9K Ratings
🗓️ 10 September 2018
⏱️ 9 minutes
🧾️ Download transcript
Hosted on Acast. See acast.com/privacy for more information.
Click on a timestamp to play from that location
0:00.0 | This TED Talk features AI and music entrepreneur Pierre Burrough, recorded live at TED 2018. |
0:09.2 | About two and a half years ago, I've watched this movie called Her, and it features Samantha, |
0:15.1 | a superintelligence form of AI that cannot take physical form. And because she can't appear in photographs, |
0:22.9 | Samantha decides to write a piece of music |
0:24.6 | that will capture a moment of her life just like a photograph would. |
0:29.3 | As a musician and an engineer |
0:31.2 | and someone raised in the family of artists, |
0:34.1 | I thought that this idea of musical photographs was really powerful. |
0:38.4 | And I decided to create an AI composer. |
0:41.5 | Her name is Ava, and she's an artificial intelligence |
0:44.9 | that has learned the art of music composition |
0:46.7 | by reading over 30,000 scores of history is greatest. |
0:50.9 | So here's what one score looks like to the algorithm |
0:52.9 | in a matrix-like representation, and here's what 30 score looks like to the algorithm in a matrix-like representation. |
0:55.0 | And here's what 30,000 scores written by the likes of Mozart and Beethoven look like in a single frame. |
1:02.0 | So using divinal networks, Ava looks for patterns in those scores. |
1:08.0 | And from a couple of bars of existing music, it actually tries to infer what notes should |
1:14.9 | come next in those tracks. |
1:16.6 | And once Ava gets good of those predictions, it can actually build a set of mathematical |
1:21.3 | rules for that style of music in order to create its own original compositions. |
1:27.3 | And in a way, this is kind of how we humans compose music too. |
1:31.2 | It's a try and error process during which we may not necessarily get the right notes all the time, |
... |
Transcript will be available on the free plan in -2389 days. Upgrade to see the full transcript now.
Disclaimer: The podcast and artwork embedded on this page are from TED, and are the property of its owner and not affiliated with or endorsed by Tapesearch.
Generated transcripts are the property of TED and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.
Copyright © Tapesearch 2025.