Ok I figured it out in my brain. It's mostly about the compression, not the speed or mem used or data size....don't get me wrong that helps tons but a better pattern finder is way better, because if we place 2 curves on each other and one does bit better, and are trained fully! and don't really benefit anymore, then it won't matter how much more data you feed the curve below, it won't ever really reach the higher curve.
/ / / / / / / / / / ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T6761a13445e5864b-M9974b76826652196a14be0e1 Delivery options: https://agi.topicbox.com/groups/agi/subscription
