Eck: Low-temperature AI models produce caricatures rather than authentic samples
Doug Eck · Making Music and Art Through Machine Learning - Doug Eck of Magenta · Y Combinator · Jul 21, 2017 · at 22:40
Doug Eck, research scientist at Google Magenta, explains how compressed neural network representations yield idealized averages when sampled at low temperatures.
0:00 / 0:27exact quote · 27.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“If you sample from Sketch RNN with very low temperature, meaning with, like, without a lot of noise in the system, you actually get what, like, if you want to squint your eyes and break philosophy is like the platonic cat. You know, you get a cat that looks more like a cat anyone would draw. Sort of the average cat. And I think that's sort of what we're getting from these time series models as well. They, they're kind of giving you something that's more a caricature than a sample, right?”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Doug Eck
Eck: Alex Graves advanced LSTMs more than anyone, including its creator
“Among the three of us, by far, Alex Graves has done the most with LSTM. So he continued, after he finished his PhD, and he continued doggedly to try to understand how recurrent neural networks worked, how to train them, and how to make them useful for sequence…”
Eck: Untrained listeners rated Magenta compositions as more Bach-like than Bach
“When we put these tunes out for, like, untrained listeners to listen to, they sometimes voted them as sounding more Bach-y”
Eck: As of 2017, AI cannot generate a single coherent text paragraph
“So, so everybody understands that's listening or watching, you know, we can, we can't generate a coherent paragraph, right? So, I don't mean we, magenta. I mean, kind of we, humanity.”
Eck: Magenta aims to build creative tools, not act as artists
“The reason that I put that quote there, I think, is to be honest with the division between engineering and research and artistry, and to not think that what I'm doing is being a machine learning artist, but we're trying to build interesting ways to make new ki…”
Eck: Users' first instinct with AI art models is breaking them
“The first thing you're gonna do, if you think, if someone comes to you and says, here's this really smart model that you can make art with, what are you gonna do? You're gonna try to show the world that it's a stupid model, right? But maybe the way that, maybe…”
Eck: Magenta's generated AI music is not yet good enough for testing
“I, at least for Magenta, I haven't felt like the quality of what we've been generating has been good enough to bother, so to speak. Like you find it, you cherry pick, you find some good things, you're like, okay, this model trains, and it's interesting, and no…”