On Sat, Mar 30, 2024, 7:35 PM John Rose <[email protected]> wrote:
> On Saturday, March 30, 2024, at 7:11 PM, Matt Mahoney wrote: > > Prediction measures intelligence. Compression measures prediction. > > > Can you reorient the concept of time from prediction? If time is on an > axis, if you reorient the time perspective is there something like energy > complexity? > > The reason I ask is that I was mentally attempting to eliminate time from > thought and energy complexity came up... verses say a physical power > complexity. Or is this a non-sequitur. > Prediction order doesn't matter because p(a)p(b|a) = p(b)p(a|b). In either case the compressed size is -log(a,b). The energy problem is how to implement a 600T parameter sparse (density 10^-7) neural network at 10 Hz on 20 watts? You would have to shrink transistors to smaller than silicon atoms. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5c24d9444d9d9cda-M4e2624dc2a10762d0e27c69e Delivery options: https://agi.topicbox.com/groups/agi/subscription
