Connectionists: New from the MIT Press: Cognitive Robotics, edited by Angelo Cangelosi and Minoru Asada

[Juyang Weng]

Dear Minoru and Angelo,
Thank you very much for willing to accept "task-nonspecificity" and
"conscious learning".
I will wait a little before clarifying why "task-nonspecificity" and
"conscious learning" are necessary to address the well-recognized
brittleness of autonomous robots.
Many people on the lists do not have sufficient time to carefully read the
reasons explained in the related publications.
Best regards,
-John

On Tue, May 24, 2022 at 9:43 AM asada+otri <asada at otri.osaka-u.ac.jp> wrote:

> Juyang,
>
> Long, long time no see.
>
> juyang.weng> I would like to congratulate on the publication of the book.
>
> Thanks.
>
> juyang.weng> I browsed the book quickly.   I would like to give you some
> quick feedback:
>
> Thank you for your quick feedback. If we have a chance to revise the
> book, we may consider your points. Thanks again in advance.
>
> Best,
>
> -- Minoru and Angelo
>
>   -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
>   Minoru Asada, Vice-President of International Professional
>   University of Technology in Osaka
>   3-3-1 Umeda, Kita-ku, Osaka 530-0001, Japan
>   https://www.iput.ac.jp/osaka
>   Tel. +81-6-6347-0111 Fax. +81-6-6345-3456
>
>   Minoru Asada (Specially-Appointed Professor) asada at otri.osaka-u.ac.jp
>   Strategic Adviser: Symbiotic Intelligent System Research Center
>   Open and Transdisciplinary Research Initiatives, Osaka University
>   https://sisrec.otri.osaka-u.ac.jp
>   1-1 Yamada-Oka, Suita, Osaka 565-0871, Japan
>   Tel. +81-6-6879-7347 Fax. +81-6-6879-4843
>
>   Minoru Asada (Visiting Professor)
>   Chubu University Academy of Emerging Sciences
>   1200 Matsumoto-cho, Kasugai, Aichi 487-8501, JAPAN
>
>   Minoru Asada (Principal investigator)
>   Center for Information and Neural Networks (CiNet)
>   National Institute of Information and Communications Technology (NICT)
>   1-4 Yamadaoka, Suita City Osaka, 565-0871
>   https://cinet.jp/japanese/people/20161868/
>
>   -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
>
>
> juyang.weng>
> juyang.weng> (1) About developmental robots:  Missed task-nonspecificity
> which is the
> juyang.weng> flagship concept of Autonomous Mental Development (AMD)
> published in
> juyang.weng> Science 2001.   For example, the six principles in Fig. 3.3
> do not include
> juyang.weng> task-nonspecificity,  The principles in Fig. 3.3 are vague,
> not unique
> juyang.weng> timewise.  They appear to have appeared many times before
> 2000 when
> juyang.weng> computational development was discussed in Workshop on
> Development and
> juyang.weng> Learning. For example, what was new with "Embodiment" for
> robotics at all?
> juyang.weng>  Is there a robot that does not have a body?   One important
> concept is
> juyang.weng> "grounded" learning as in the acronym GENISAMA!   Another
> juyang.weng> unfortunate phenomena throughout the book is that I do not
> see any
> juyang.weng> task-nonspecific emergent representations.  All the
> representations that I
> juyang.weng> have seen are symbolic in nature.
> juyang.weng>
> juyang.weng> (2) The material in the book does not seem to give hope to
> end the
> juyang.weng> brittleness of robotics.  Chapter 23 does not provide any
> architectures nor
> juyang.weng> algorithms for conscious learning.  Developmental Networks,
> DN-1, DN-2 and
> juyang.weng> now DN-3 suggest that conscious learning is a necessary
> condition for
> juyang.weng> animals to develop animal-like intelligence (and awareness of
> the external
> juyang.weng> world and self).  From the following paper, robots seem to
> need conscious
> juyang.weng> learning to end their high brittleness (e.g., igerant about
> whether it is
> juyang.weng> doing any task well).   I have received  some strong
> resistance to
> juyang.weng> conscious learning (e.g., not willing to even review), but
> this resistance
> juyang.weng> to new science should fail soon like any resistances to new
> sciences.
> juyang.weng>
> juyang.weng> (3) I looked through the book series that Ron Arkin edited.
> I was in his
> juyang.weng> office about an AMD book that I was writing.   The book
> series that Ran
> juyang.weng> Arkin edits lacks task-nonspecificity and also conscious
> learning.  Maybe
> juyang.weng> the series can improve soon if Ron is open minded.
> juyang.weng>
> juyang.weng> J. Weng, "An Algorithmic Theory of Conscious Learning", in
> Proc. 2022 3rd
> juyang.weng> International Conf. on Artificial Intelligence in Electronics
> Engineering,
> juyang.weng> pp. 1-10, Bangkok, Thailand, Jan. 21-23, 2022. PDF file
> juyang.weng> <
> http://www.cse.msu.edu/~weng/research/ConsciousLearning-AIEE22rvsd-cite.pdf
> >
> juyang.weng> .
> juyang.weng>
> juyang.weng> Best regards,
> juyang.weng> -John
> juyang.weng> ---
> juyang.weng> Juyang (John) Weng
>
>

-- 
Juyang (John) Weng
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20220524/558dca31/attachment.html>