I think the most relevant implication of the No Free Lunch Theorem here is
that a general intelligence is mathematically impossible.

Do you agree?


On Thu, Oct 1, 2020 at 2:08 PM Jim Bromer <[email protected]> wrote:

> 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 <https://agi.topicbox.com/latest>*
> / AGI / see discussions <https://agi.topicbox.com/groups/agi> +
> participants <https://agi.topicbox.com/groups/agi/members> + delivery
> options <https://agi.topicbox.com/groups/agi/subscription> Permalink
> <https://agi.topicbox.com/groups/agi/Ta433301e9ac5fb42-M86b52b5179bf45be4b97d5cf>
>


-- 
Dr. Danko Nikolić
www.danko-nikolic.com
https://www.linkedin.com/in/danko-nikolic/

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/Ta433301e9ac5fb42-Ma1012b292089c83ab4e386aa
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to