Stephen Downes

Knowledge, Learning, Community

If you stare into static long enough you can eventually see shapes. That's how your brain works; as a neural network it functions through a process of recognition, picking out familiar (ie., previously perceived) images out of background noise. Not all of our experiences are of static, of course, so our recognition of images is more predictable, more stable, and they settle in our conception as material things, as objects. This article in the Guardian, based on a report from Google, dramatically illustrates how that process works. Google image-recognition algorithms were fed both static and background images and were asked to extract dogs, animals, buildings, etc. This is what the images look like when they do that. And it is, suggests the time, an insightful glimpse into robot consciousness. And, I would submit, human consciousness as well.

Today: 1060 Total: 1070 [Direct link] [Share]

Image from the website
View full size


Stephen Downes Stephen Downes, Casselman, Canada
stephen@downes.ca

Copyright 2024
Last Updated: Mar 29, 2024 10:36 a.m.

Canadian Flag Creative Commons License.

Force:yes