Re: neural networks being purported as KR?

Dear Paula,I haven't been following closely, but have dipped in.I like to
think that this helps me to keep open to different ideas.Perhaps it does?Paula,
you say"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 - it's 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)"
I think that what I have to say here is relevant?I have been thinking a lot
about how understanding is formed between people.What is it to understand, what
is a "common language"? What is the domain of discourse, the public domain (not
to confuse the two), the shared?Reading through Prashant Parikh's Language and
Equilibrium (M.I.T. Press 2010) I am finding something missing which I think has
to do with relative scale as opposed to scale-free.I believe that unknown to me
my ideas have been encouraged by my professional interest in Lacanian thought. I
understand that the reason that topology features so centrally in Lacanian
thought is because of its relationship to scale, the intersection of the
eponymous Mobius strip where to folds into itself which consists of points
described asproximate  to each other.If language is divided down, atomised can
it become, at what point does it cease to be a means of understanding?What I
really mean is something quite literal, if speakers become ever more isolated
and develope their own "private" languages how do we reach what is shared?The
theme is real, there are people who are more rather than less like this, it has
been explored in literature and it is also expressed as literature. The Mad
Hatter in Alice in Wonderland famously might be as both.Not least, it has been
explored in philosophy, importantly so by Wittgenstein.Your comment highlights
cognitive function and conversation, juxtaposing that with something incapable
of either, your putative neuron.What I am pointing out is that as people who do
have both cognitive functions and are able to converse, still, that ability can
break down. Actually, this ability can be taken away from people,
surreptitiously and to some extent, before anyone cries foul!As a therapist, I
have to be concerned about when cognitive function fails in an individual and
the nature and extent of the damage.As a member of society, I have other,
broader, concerns about the processes of fragment, distort and sell on
mechanisms. Mechanisms that necessarily have no sense of scale as to what
constitutes a fragment, never mind the emphasis that Parakh places on context.
Adam Saltiel
If anyone on the list is interested at all I am convening a conference, the
first of its kind, on these topics, on Saturday 21 September, Amnesty
Internation, London.See more here:AAPWeb.website  





On Sat, Jul 27, 2019 12:03 AM, Paola Di Maio paoladimaio10@gmail.com  wrote:
Thank you all who replied (from different lists)and apologies for cross posting,
also apologise for sending links to articlesbehind the paywall
I did not find any reference to subsymbolic KR in that article, if that is so,
such definition for NN should be specifiedas being subsymbolic . There's a huge
difference.
Achieszka - and others - this must be the part of the semantic web that I never
understood, and maybewhy 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
meaningaggregating smaller units, say, lexemes or parts of speech but...at
system level, there can be no function, nor process, nor logical integrity
without the coherentintegration 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 stackSymbols 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 KRto 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> 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> 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> 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
downas 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)