Hi Danko

Tricky question. I think the a-linear properties of general intelligence have 
the potential to contradict NFL.

I don't see that as being a significant problem for the development of AGI.

I've probably spent the last 22 years working in this space. As posited, NFL 
presents as a hard system. These days, architects recognize a hard system as a 
logical part of a holistic system, which includes a soft system as well.

I think general intelligence emerges from thermo-dynamical entanglement of 
environmentally-specific combinations of adaptive, hardsoft systems. Perhaps, 
this notion could be proven via net, algorithmic X optimizations, which 
intentionally resulted in delta+ performance? Notwithstanding the notion of 
NFL+, the potential had to be inherent in the original design first. I'd 
contend it goes to root architecture.

By such argument then; no hard contradiction would ultimately exist, but a 
relative value of GIGO probably would apply.

Robert Benjamin

________________________________
From: Danko Nikolić <[email protected]>
Sent: Monday, 03 February 2020 14:44
To: AGI <[email protected]>
Subject: [agi] General Intelligence vs. no-free-lunch theorem

Hi,

I am curious to learn what the people here think about the idea that the notion 
of general intelligence contradicts the no-free-lunch-theorem.

Do you guys agree that a contradiction exists? If so, is that a problem? Would 
that mean that no form of general intelligence could ever exist?

Also, does anyone here undertake any explicit efforts to circumvent this 
contradiction?

Thanks a lot.

Danko

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/T353f2000d499d93b-Ma4ccf9e1dff0d229b7ab68cb>

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T353f2000d499d93b-M6c08e5e33efa14620f964389
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to