Yes, storing temporal patterns works fine, the same as text. The easiest example that prooves it is Cellular Automata, that is it!
Doing vision is cool if you change the semantics slightly, doing markov chains with 3d vectors might end up better, because there is more invarience -> therefore -> less patterns to store for the same amount of content. To get that to happen, you go through a converter program, before u start storing patterns. It does work in 2d, just with colours, but that would be more designed for 2d scrolling video games, then it would be ok, just to leave it as the video picture itself directly. I had some examples of me doing it, but its all deleted now sorry, and I have to wait for my next attempt before I get some more action of doing it again. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5b614d3e3bb8e0da-M46cbcb80420b4ff3395bed33 Delivery options: https://agi.topicbox.com/groups/agi/subscription
