Paq mixes the probabilities from the context models by stretching: x =
ln(p/(1-p)), then weighted summation using a neural network, then squashing
the output with the inverse function p = 1/(1+e^-x). The weights are
updated as w += Lx(b-p) where b is the actual bit, b-p is the output error,
x is
> Now I'm 9MB away from world record.
Go go go!
--
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T409fc28ec41e6e3a-M17568031eee8e1f258936548
Delivery options: https://agi.topicbox.com/groups/agi/subscription