Dear AGI Chatterboxes: What is the difference in scientific value between interpolation and extrapolation?
On Fri, Dec 6, 2019 at 5:19 AM <[email protected]> wrote: > They didn't discover it. And they say it's often avoided. All they did was > verify it screws up on most of the architectures. It should be clear that > any upward curve in the graph is related to non-patterns during > compression, it's just compression, better model = less error/smaller > model. We already know why the curve shoots down, you see. Btw to survive > in the universe you need be prepared for all possible situations, and > common problems. So having a diverse model allows you to know a lot while > store very little, it allows you to survive better. > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/Tc1f2c133ae3e4762-M3c016dffefcf634f92b503ad> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tc1f2c133ae3e4762-M618fe258792a0c67c9a160a3 Delivery options: https://agi.topicbox.com/groups/agi/subscription
