Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity

arXiv.org Artificial Intelligence

I postulate that human or other intelligent agents function or should function as follows. They store all sensory observations as they come - the data is holy. At any time, given some agent's current coding capabilities, part of the data is compressible by a short and hopefully fast program / description / explanation / world model. In the agent's subjective eyes, such data is more regular and more "beautiful" than other data. It is well-known that knowledge of regularity and repeatability may improve the agent's ability to plan actions leading to external rewards. In absence of such rewards, however, known beauty is boring. Then "interestingness" becomes the first derivative of subjective beauty: as the learning agent improves its compression algorithm, formerly apparently random data parts become subjectively more regular and beautiful. Such progress in compressibility is measured and maximized by the curiosity drive: create action sequences that extend the observation history and yield previously unknown / unpredictable but quickly learnable algorithmic regularity. We discuss how all of the above can be naturally implemented on computers, through an extension of passive unsupervised learning to the case of active data selection: we reward a general reinforcement learner (with access to the adaptive compressor) for actions that improve the subjective compressibility of the growing data. An unusually large breakthrough in compressibility deserves the name "discovery". The "creativity" of artists, dancers, musicians, pure mathematicians can be viewed as a by-product of this principle. Several qualitative examples support this hypothesis.


Why I want my own music in the age of streaming

Mashable

I have no interest in your streaming. When it comes to the music I love, I'm possessive to a fault. I want to own it all. Case in point: on April 14, Kendrick Lamar released "DAMN.", I immediately bought the album on iTunes, because a version in my preferred format, vinyl, won't be available until July.


This adorable stuffed animal robot helps your kid stay curious

Mashable

Just to let you know, if you buy something featured here, Mashable might earn an affiliate commission. Parenting and AI aren't usually something you think of as going hand in hand, but the people behind this Kickstarter campaign have created a robot that both parents and kids will love. Parents, you know that kids ask a lot of questions. Well, get ready to let out a sign of relief -- this cuddly little guy will answer all of them without ever getting annoyed. Woobo was designed to be a companion for children that encourages their curiosity in a fun and educational way.


Four-Armed Marimba Robot Uses Deep Learning to Compose Its Own Music

IEEE Spectrum Robotics

The Georgia Tech Center for Music Technology, led by Gil Weinberg, has a reputation for doing incredible musical things with robots, with a mix of creativity and technical expertise in robotics and AI. We've seen projects like a cybernetic second arm for a drummer, a cybernetic third arm (!) for a drummer, and a bunch of interesting research on ways that robots can dynamically collaborate with humans in the context of improvisational music. That last thing usually features Shimon, a four-armed expressive robotic marimba player, which can analyze music in real time and improvise along with human performers. It's an impressive thing to watch, but Shimon's talents were mostly restricted to riffing on what other human musicians were doing. Now, Shimon has leveraged deep learning to create structured and coherent and totally unique compositions of its very own.


Four-Armed Marimba Robot Uses Deep Learning to Compose Its Own Music

IEEE Spectrum Robotics

The Georgia Tech Center for Music Technology, led by Gil Weinberg, has a reputation for doing incredible musical things with robots, with a mix of creativity and technical expertise in robotics and AI. We've seen projects like a cybernetic second arm for a drummer, a cybernetic third arm (!) for a drummer, and a bunch of interesting research on ways that robots can dynamically collaborate with humans in the context of improvisational music. That last thing usually features Shimon, a four-armed expressive robotic marimba player, which can analyze music in real time and improvise along with human performers. It's an impressive thing to watch, but Shimon's talents were mostly restricted to riffing on what other human musicians were doing. Now, Shimon has leveraged deep learning to create structured and coherent and totally unique compositions of its very own.