As we discussed, Brett, I agree on most of the principles above. But your
implementation is not defined / justified strictly bottom-up. To me, that means
pixels-up cross-comparison, which defines variance: differences/gradients, and
invariance: match/compression. Without that, your specifics is bound to be
largely arbitrary and there is no way to avoid endless conceptual confusion.
That's what I see in your fixation on binons: substrate-bound vs. functional
thinking, and Weber-Fechner’s Law: superficial, limited, and
biologically-specific statistical observation.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T8366cc740ec68376-M47f294feb31a18b7b9af1463
Delivery options: https://agi.topicbox.com/groups/agi/subscription
