Re: [ontolog-forum] Different methods for different tasks (was symbolic equation

Hello John, thank you
Thank you for the slides-  to say cat is on the mat other than language I
like existential and conceptual graphs the best, they are the most
computatioanally efficient!

I think when we use the word symbolic we may have start disambiguating, at
which level.
Of course, computational symbols are alphanumeric. (this is what Ng referes
to I think)

  Are pictures that do not contain alphanumeric characters symbolic? I
think so (a picture of an umbrella or a house is highly symbolic from a
semiotic point of view

is musical notation symbolic, I think so
  Are audio signals, sounds, also symbols?  more directly related to
perception

For more understanding of symbols, we study signs, semiotic, etc

But here I was referring to the expression symbolic equation does not seem
to make sense as a symbolic knowledge representation

The use of alphanumeric symbols had nothing to do with symbolic AI, whereby
symbolic AI adopts symbolic KR, as we learn also from your book.
But in ML papers now people are mixing the two levels-  and in addition to
various computational headaches including p-values and general
understandability and reproducibility fo the algorithms, now we have to be
careful to see what exactly are they doing and saying when they say
symbolic?  Symbolic KR can be used to explain that-

The sentence you attribute to me below actually Alex's r. no worries

> PDM>ALEX But I am in the position that most important and even terrific
> is that they begin to train ANN with symbolic input and/or output, getting
> exciting results.



PDM

On Sun, Jun 28, 2020 at 2:26 AM John F. Sowa <sowa@bestweb.net> wrote:

> Paola,
>
> Every ANN that has ever been designed and used maps symbols to symbols.
> For examples, please look at slide 36 of http://jfsowa.com/talks/eswc.pdf
> .
>
> The table at the top of the slide is by Andrew Ng, who is an  expert in
> designing and developing ANNs.  The comments about that table are summaries
> of what Ng said in the video, which I cited at the bottom of that slide.
>
> PDM> But I am in the position that most important and even terrific is
> that they begin to train ANN with symbolic input and/or output, getting
> exciting results.
>
> For pattern recognition, the input for a typical  ANN is a matrix of
> symbols (triads of numbers for Red, Green, and Blue) that represent the
> colors of pixels in a photograph.  The output is a symbol (or structure of
> symbols) that describes the image represented by those pixels.
>
> In the Alpha Go system, which beat the world champion at Go, the ANN for
> the evaluation function mapped symbols that represented stones on a Go
> board to symbols (numbers) that estimated the strength of a particular Go
> position for one player or the other.
>
> Although the Alpha  Go designers gave most of the credit to the ANN, the
> system was actually a hybrid.  It used many symbolic steps to play the game
> and search different options.  There was only one step that used an ANN:
> evaluate a board position to estimate which player had a better position.
>
> Research issue:   Instead of using one or more ANNs to do all the steps of
> cognition, find some way of subdividing the task into a variety of
> different kinds of tasks that must be performed.   Then determine which of
> those tasks could be handled better by an ANN or by some symbolic method.
>
> John
>
> --
> All contributions to this forum are covered by an open-source license.
> For information about the wiki, the license, and how to subscribe or
> unsubscribe to the forum, see http://ontologforum.org/info/
> ---
> You received this message because you are subscribed to the Google Groups
> "ontolog-forum" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to ontolog-forum+unsubscribe@googlegroups.com.
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/ontolog-forum/e97196ea75a2848cde3d196a3691959a.squirrel%40webmail2.bestweb.net
> <https://groups.google.com/d/msgid/ontolog-forum/e97196ea75a2848cde3d196a3691959a.squirrel%40webmail2.bestweb.net?utm_medium=email&utm_source=footer>
> .
>