On Tue, Nov 9, 2021 at 6:08 AM John Rose <[email protected]> wrote:

> ...It is less obvious that there is not a sharp boundary among all
> compressors with the data they compress that are classified exclusively as
> either lossy or lossless implemented in physical reality. These
> compressions have value too for various reasons...
>

First of all, in the word "value" you finally touch on the relevant
characteristic of lossy compression that brings them into confluence with
sensors and measurement:  the value function that drives both evolution and
AGI's decisions (aka "utility function") is an open parameter in AGI
formulations such as AIXI = AIT⊗SDT = Algorithmic Information Theory ⊗
Sequential Decision Theory.  Lossy compression belongs on the Sequential
Decision Theory side of the ⊗ just as does the fitness function of
evolution belong on the decision side of biological evolution.  It's a
matter of economics -- of engineering -- of technology -- of "ought" but
NOT of "is".

"is" belongs on the AIT side of the ⊗.  "is" is lossless but only with
respect to the data provided by the evolutionary process in the form of
sensors.  The cognitive process also has economic constraints about what
data can be retained -- memorized -- and that _to_ involves a "lossy"
process that limits what AIT can do -- even given infinite resources, which
are not available to AIT in any event.  But that doesn't mean AIT throws
data away -- it just means AIT never has certainty that it has achieved the
smallest, lossless, memorization of the data provided by evolution.

So, the presence of "sharp boundaries" depends on one's ability to draw the
corresponding distinctions.  For instance, humans unaided by technological
civilization draw "sharp boundaries" between green and red but do not
between UHF and VHF photons.

Once again my dear Mr. Rose, we are discussing sensors and measurements --
not compressors.  You are militantly category error-prone on this topic.
Why?

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T5ff6237e11d945fb-M0e658f31439f89825ed4ebee
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to