I am learning a little. The no free lunch theorem depends on the analysis of an
imperfect system that will lead to perfect knowledge. But in real world it is
possible that someone might come up with a solution to a complicated problem
that would have to be heavily developed in order to be tested. Reality
intelligence deals with that situation all the time. We sometimes ignore steps
to solutions just because of the costs of development and testing would be so
high. That is the actual nature of search. My argument is that the No Free
Lunch theorem, while a useful bit of insight, is not actually what is keeping
us from making useful discoveries in AI or AGI. The universe is open to an
abundance of useful discoveries *just because* we do not have perfect
knowledge, and most of us could stumble over a great discovery without
realizing it. By looking carefully at practical experiences, even without
making any great discoveries, we can start to better deal with the real world.
Now, you might say that you cannot think outside the box because that is the No
Free Lunch cost of your everyday thinking. But do any of you actually believe
that?
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/Ta433301e9ac5fb42-M86b52b5179bf45be4b97d5cf
Delivery options: https://agi.topicbox.com/groups/agi/subscription
