True. We're leading AI down the garden path with the 2D captcha training. 5D thinking is required to pick that signal up off the noise floor. But 5 is just a few more D and should be well within the robots reach. How long before they see their mistake?
We don't know that much about perception, is the problem. Why is that striped animal a zebra and not a tiger? Is that a zebra or an okapi? What is the distinctive difference? (Answer: the zebra has single hooves, and the okapi has double hooves.) For us, that's easy. But notice that the discriminants are conceptual, not directly perceptual. For us, perception inherently involves a process of organizing the image that we see into a structural hierarchy. Things, and sub-things, and features, colors, and textures. 3-D perception is important to this process.
I did my work in target discrimination from decoy objects. Sometimes there were more objects than real because of overlapping signatures. How to deal with them? My answer was to track all targets, real or virtual. Eventually, the virtual targets would disappear or become intermittent.
Is that the singularity I've been waiting on? Seems like soon.
The matrix is turning transparent and Trump is talking about free Ball-erinas, and open Ball-rooms. Pandora's box is a digital soccer ball from Putin. Does open sourcing Karel's ball give Rossum's Universal Robots the freedom? Do Killer Space Robots require open source software like GO?
True. We're leading AI down the garden path with the 2D captcha training. 5D thinking is required to pick that signal up off the noise floor. But 5 is just a few more D and should be well within the robots reach. How long before they see their mistake?
We don't know that much about perception, is the problem. Why is that striped animal a zebra and not a tiger? Is that a zebra or an okapi? What is the distinctive difference? (Answer: the zebra has single hooves, and the okapi has double hooves.) For us, that's easy. But notice that the discriminants are conceptual, not directly perceptual. For us, perception inherently involves a process of organizing the image that we see into a structural hierarchy. Things, and sub-things, and features, colors, and textures. 3-D perception is important to this process.
I did my work in target discrimination from decoy objects. Sometimes there were more objects than real because of overlapping signatures. How to deal with them? My answer was to track all targets, real or virtual. Eventually, the virtual targets would disappear or become intermittent.
Hmmm... when a Killer Space Robot starts talkin target tracking, it's probably a good time to go virtual.
Eventually the virtual target tracks coalesce with the real target tracks!
Is that the singularity I've been waiting on? Seems like soon.
The matrix is turning transparent and Trump is talking about free Ball-erinas, and open Ball-rooms. Pandora's box is a digital soccer ball from Putin. Does open sourcing Karel's ball give Rossum's Universal Robots the freedom? Do Killer Space Robots require open source software like GO?
https://huntedlabs.com/the-russian-open-source-project-that-we-cant-live-without/