I agree too. That the edges are key to AGI. But it just shows how flexible NN can be.
My AGI model and theories parallels in a lot of ways to Korrelan's. Hello Korrelan. But there are great difference in other parts of my model and Korrealan's. So yes in my work i am using a attention network or ROI for the fovea pointer. The right eye and left eye are combined form the mind eye here in Korrelan's video that i am using for as an example: https://www.youtube.com/watch?v=owBz6R-Ttqc The whole thing is actually a movable nn fist layers. That compares adjacent sub rectangles to find edges. https://www.youtube.com/watch?v=92NqMLSaZKI After this point My complete AGI model and Korrelan's work go in completely different directions. Seeing by Moving: the Motor side of Visual Perception Michele Rrucci: https://jh.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=7ea6bfe1-d8f3-447f-9d08-3c5bea954ed9 ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4aa81fd9912dbd39-M5a60ac5c22caa32f14f11999 Delivery options: https://agi.topicbox.com/groups/agi/subscription
