Re: neural networks being purported as KR?

Appreciate that message. Just wanted to second the fact that true KR goes much, much deeper than mathematics (though, as we know it right now). Neural networks, while dynamic and nonlinear still do not capture the unexplainable functions of the brain.

I do find it quite interesting that every time we get this deep, Buddhism is always mentioned. :)

Sent from my iPhone

On Jul 26, 2019, at 5:10 PM, Paola Di Maio <paoladimaio10@gmail.com<mailto:paoladimaio10@gmail.com>> wrote:

Thank you all who replied (from different lists)
and apologies for cross posting, also apologise for sending links to articles
behind the paywall

I did not find any reference to subsymbolic KR in that article, if that is so, such definition for NN should be specified
as being subsymbolic . There's a huge difference.

Achieszka - and others - this must be the part of the semantic web that I never understood, and maybe
why the sw that some of us are hoping for,  has not yet happened  (I got as far as microtheories)

Now I understand also the thinking behind the bits about the logic disjunction which chill my bones.

Semantics, as in..... ''relating to meaning in language or logic'' cannot be supported by sub symbolic KR,
can it?   What are the languages of SSKR?  I cannot envisage 'discourse or argumentation' being possible
(unless its ahead and I cant see it)

The point  is that SSKR does not support Logic, which is the foundation of intelligent function in human and systems

You can argue that computational semantics can be more granular and express meaning
aggregating smaller units, say, lexemes or parts of speech but...
at system level, there can be no function, nor process, nor logical integrity without the coherent
integration of the parts (the intelligence bit)

A lump of neurons dont make a brain!!!!

This article says:
The subsymbolic representation of the world often corresponds to a pattern that mirrors the world as described by the biological sense organs.
https://academic.oup.com/logcom/article-abstract/23/3/627/1029379?redirectedFrom=fulltext


An individual neuron, is not capable of cognitive function beyond the  synapsis
(from what we know).

I cannot  have ANY kind of intelligent interaction  with a single neuron - its like trying to have a conversation with an amoeba
 or with a single brain cell, or to make eye contact with a cell in the retina
 Not likely  (beyond elemental signal exchange)

Agree perhaps symbolic and subsymbolic KR must be integrated, thanks DR for pointing to that article

I found this article useful also to explain the KR stack
Symbols and subsymbols for representing knowledge: a catalogue raisonne
https://www.ijcai.org/Proceedings/89-1/Papers/001.pdf


I wonder, John and all,  do you think it is reasonable to suggest that for each
set of sub symbolic KR, there shoudl correspond a set of symbolic KR
to support some kind of integration of the different levels

I wonder

Thanks to all

PDM





On Fri, Jul 26, 2019 at 11:00 PM Agnieszka Ławrynowicz <agnieszka.lawrynowicz@cs.put.poznan.pl<mailto:agnieszka.lawrynowicz@cs.put.poznan.pl>> wrote:
Hi All,

Of course deep neural networks may be seen as form of knowledge representation in my opinion, more precisely they are sub-symbolic or connectionist representations versus symbolic representations which are the standard in Semantic Web.
Though it is not „latest KR”, but have been there for a long time under exactly the above name (sub-symbolic representations).

Best Regards and cheers,
Agnieszka



Wiadomość napisana przez Diogo FC Patrao <djogopatrao@gmail.com<mailto:djogopatrao@gmail.com>> w dniu 26.07.2019, o godz. 16:40:

Hi Paola

I'd say a NN is not as "knowledgy" as a decision tree. I would argue that NN is a mathematical model that compiles previous data representing cause/consequences, so it's the same type of knowledge as, say, a logarithm table, versus the type of knowledge the infinte sum formula for evaluating logarithms would represent.

They certainly don't look the same thing to me.

Cheers,

dfcp

--
diogo patrão




On Thu, Jul 25, 2019 at 11:58 PM Paola Di Maio <paola.dimaio@gmail.com<mailto:paola.dimaio@gmail.com>> wrote:
Sorry to bang on this topic, but its the task at hand at the moment

I just found an article, which is good scientific survey then  purports NN as a type of KR
(casually sneaks in NN as the latest KR)

This is published in a Springer peer reviewed publication and my makes all of my hairs stand up on my head

This is the kind of rubbish that without further qualification is being passed down
as the latest research, and  which the future generations of AI scientists are being fed-

wonder if anyone else has a problem with this proposition
(sign of the times?)
I am doing my best within my means to identify and contain this peril

Article https://link-springer-com.nls.idm.oclc.org/article/10.1007/s00170-018-2433-8


A survey of knowledge representation methods and applications in machining process planning

The machining process is the act of preparing the detailed operating instructions for changing an engineering design into an end product, which involves the removal of material from the part. Today, machining ...

Xiuling Li, Shusheng Zhang, Rui Huang… in The International Journal of Advanced Manu… (2018)