Thanks for writing this.
One question I have about this and other work in this area is the training / deployment distinction. If AIs are doing continual learning once deployed, I'm not quite sure what that does to this model.
Should
serious problems with Boltzmann machines
instead read
serious problems with Boltzmann brains
?
Thanks for writing this.
One question I have about this and other work in this area is the training / deployment distinction. If AIs are doing continual learning once deployed, I'm not quite sure what that does to this model.