James Bowery wrote:
If you are acting on the environment to obtain information, you are
"supervised" by the environment and your action involves decision
theory parameterized by a value function in an explore/exploit
tradeoff.?? ??This corresponds to engineering/technology and it is what
living things do.
If your learning does not involve acquisition of information, then
your value function is to minimize the size of the program that
outputs the information you have, which has been proven to produce the
model that optimally predicts missing data (whether present or
prospective) in the sense that the model's predictions are more likely
to be correct than any other model.?? This is "unsupervised", and
corresponds to "value free science".
/me dispenses a cookie.
--
Clowns feed off of funny money;
Funny money comes from the FED
so NO FED -> NO CLOWNS!!!
Powers are not rights.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T77af318d4abfa8a8-M55e54fa2d956119987dedafd
Delivery options: https://agi.topicbox.com/groups/agi/subscription
