The paper contains: 1) A discussion of the history of how we've defined and evaluated AI so far 2) A new formal definition of intelligence + concrete guidelines for what a general AI benchmark should look like 3) A presentation of the goals of ARC and the logic behind it.
-
-
Show this thread
-
This definition is my attempt to formalize things I've been talking about for the past 10 years (in talks, conversations, on Twitter), into something useful and actionable. ARC itself has led me towards very interesting research directions, and I hope you will find it useful too.
Show this thread -
I want to emphasize that the definition provided here isn't meant to be the "one true" definition. That's not the point. Intelligence is complex, and may be different things in different contexts. Many possible definitions of intelligence or AI can be valid.
Show this thread -
Lately I've made good progress on an algorithm that is capable of solving at least part of ARC, based on a theory of cognition (autonomous abstraction) that I've been working on for a long time. I hope to be able to share these ideas & code soon
Show this thread -
The theory has been in the making since 2009. It draws significant elements from project ONEIROS (Open-ended Neuro-Electronic Intelligent Robot Operating System), which was a general AI architecture I worked on from 2009 to 2012 (then again briefly in 2014), then mostly abandoned
Show this thread -
ONEIROS started from a classic RL mindset, and centered on 1) learning modular-hierarchical "maps" of spatiotemporal features (using PMI matrix factorization as opposed to gradient descent), 2) context-switching via a form of attention, and 3) intrinsic motivation (curiosity)pic.twitter.com/fMNMkZAEIL
Show this thread -
The tagline was "cognition is a dynamic, hierarchical-modular map of the space of sensorimotor information". I also called it "map theory" -- there are perhaps two people in the world who will remember me preaching about it around 2010-2012
Show this thread -
Dr Filliat
@drFilliat may remember it because I did my best to explain it to him in 2011. I won't @ the other personShow this thread -
I think ONEIROS got a number of things right (especially given the context at the time -- this was mostly designed in 2010, with an attempt to implement a simplification of it in 2012), but ultimately it did not touch the most essential point: the nature of abstraction
Show this thread -
Which is what I'm working on now. This is fundamentally what ARC is about
Show this thread -
Fun fact: the name "Keras" derives from ONEIROS (cf. the gates from book 19 of the Odyssey)
Show this thread
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.