<div dir="ltr">Dear Minoru and Angelo,<div>Thank you very much for willing to accept "task-nonspecificity" and "conscious learning".</div><div>I will wait a little before clarifying why "task-nonspecificity" and "conscious learning" are necessary to address the well-recognized brittleness of autonomous robots.<br>Many people on the lists do not have sufficient time to carefully read the reasons explained in the related publications.</div><div>Best regards,</div><div>-John</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, May 24, 2022 at 9:43 AM asada+otri <<a href="mailto:asada@otri.osaka-u.ac.jp">asada@otri.osaka-u.ac.jp</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Juyang,<br>
<br>
Long, long time no see.<br>
<br>
juyang.weng> I would like to congratulate on the publication of the book.<br>
<br>
Thanks.<br>
<br>
juyang.weng> I browsed the book quickly. I would like to give you some quick feedback:<br>
<br>
Thank you for your quick feedback. If we have a chance to revise the<br>
book, we may consider your points. Thanks again in advance.<br>
<br>
Best,<br>
<br>
-- Minoru and Angelo<br>
<br>
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=<br>
Minoru Asada, Vice-President of International Professional<br>
University of Technology in Osaka<br>
3-3-1 Umeda, Kita-ku, Osaka 530-0001, Japan<br>
<a href="https://www.iput.ac.jp/osaka" rel="noreferrer" target="_blank">https://www.iput.ac.jp/osaka</a><br>
Tel. +81-6-6347-0111 Fax. +81-6-6345-3456<br>
<br>
Minoru Asada (Specially-Appointed Professor) <a href="mailto:asada@otri.osaka-u.ac.jp" target="_blank">asada@otri.osaka-u.ac.jp</a> <br>
Strategic Adviser: Symbiotic Intelligent System Research Center<br>
Open and Transdisciplinary Research Initiatives, Osaka University<br>
<a href="https://sisrec.otri.osaka-u.ac.jp" rel="noreferrer" target="_blank">https://sisrec.otri.osaka-u.ac.jp</a><br>
1-1 Yamada-Oka, Suita, Osaka 565-0871, Japan<br>
Tel. +81-6-6879-7347 Fax. +81-6-6879-4843<br>
<br>
Minoru Asada (Visiting Professor)<br>
Chubu University Academy of Emerging Sciences<br>
1200 Matsumoto-cho, Kasugai, Aichi 487-8501, JAPAN<br>
<br>
Minoru Asada (Principal investigator)<br>
Center for Information and Neural Networks (CiNet)<br>
National Institute of Information and Communications Technology (NICT)<br>
1-4 Yamadaoka, Suita City Osaka, 565-0871 <br>
<a href="https://cinet.jp/japanese/people/20161868/" rel="noreferrer" target="_blank">https://cinet.jp/japanese/people/20161868/</a><br>
<br>
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=<br>
<br>
<br>
juyang.weng> <br>
juyang.weng> (1) About developmental robots: Missed task-nonspecificity which is the<br>
juyang.weng> flagship concept of Autonomous Mental Development (AMD) published in<br>
juyang.weng> Science 2001. For example, the six principles in Fig. 3.3 do not include<br>
juyang.weng> task-nonspecificity, The principles in Fig. 3.3 are vague, not unique<br>
juyang.weng> timewise. They appear to have appeared many times before 2000 when<br>
juyang.weng> computational development was discussed in Workshop on Development and<br>
juyang.weng> Learning. For example, what was new with "Embodiment" for robotics at all?<br>
juyang.weng> Is there a robot that does not have a body? One important concept is<br>
juyang.weng> "grounded" learning as in the acronym GENISAMA! Another<br>
juyang.weng> unfortunate phenomena throughout the book is that I do not see any<br>
juyang.weng> task-nonspecific emergent representations. All the representations that I<br>
juyang.weng> have seen are symbolic in nature.<br>
juyang.weng> <br>
juyang.weng> (2) The material in the book does not seem to give hope to end the<br>
juyang.weng> brittleness of robotics. Chapter 23 does not provide any architectures nor<br>
juyang.weng> algorithms for conscious learning. Developmental Networks, DN-1, DN-2 and<br>
juyang.weng> now DN-3 suggest that conscious learning is a necessary condition for<br>
juyang.weng> animals to develop animal-like intelligence (and awareness of the external<br>
juyang.weng> world and self). From the following paper, robots seem to need conscious<br>
juyang.weng> learning to end their high brittleness (e.g., igerant about whether it is<br>
juyang.weng> doing any task well). I have received some strong resistance to<br>
juyang.weng> conscious learning (e.g., not willing to even review), but this resistance<br>
juyang.weng> to new science should fail soon like any resistances to new sciences.<br>
juyang.weng> <br>
juyang.weng> (3) I looked through the book series that Ron Arkin edited. I was in his<br>
juyang.weng> office about an AMD book that I was writing. The book series that Ran<br>
juyang.weng> Arkin edits lacks task-nonspecificity and also conscious learning. Maybe<br>
juyang.weng> the series can improve soon if Ron is open minded.<br>
juyang.weng> <br>
juyang.weng> J. Weng, "An Algorithmic Theory of Conscious Learning", in Proc. 2022 3rd<br>
juyang.weng> International Conf. on Artificial Intelligence in Electronics Engineering,<br>
juyang.weng> pp. 1-10, Bangkok, Thailand, Jan. 21-23, 2022. PDF file<br>
juyang.weng> <<a href="http://www.cse.msu.edu/~weng/research/ConsciousLearning-AIEE22rvsd-cite.pdf" rel="noreferrer" target="_blank">http://www.cse.msu.edu/~weng/research/ConsciousLearning-AIEE22rvsd-cite.pdf</a>><br>
juyang.weng> .<br>
juyang.weng> <br>
juyang.weng> Best regards,<br>
juyang.weng> -John<br>
juyang.weng> ---<br>
juyang.weng> Juyang (John) Weng<br>
<br>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail_signature"><div dir="ltr">Juyang (John) Weng<br></div></div>