Kornai Andras irta a kovetkezo levelet, amely hossza miatt egyben nem
jelenhetett volna meg, ezert Andras keresere kivetelesen beletettem a
szerkesztoi uzenetbe.
Jozsi. /HIX/
=================================================
Felado:  (Andras Kornai)
Temakor: Az utolso1 szo1 joga1n
- - - - - - - - - - - - - - - - - - - - - - - - -
Tisztelt FORUM-ozo1k!
Felmeru2lt a gondolat hogy minden kile1po3 i1rja meg "az utolso1 szo1
joga1n" hogy tulajdonke1ppen mi is vette ra1 erre a le1pe1sre.
Miuta1n a le1nyeget szerintem Ro1na-Tas A1kos ma1r ele1g jo1l
megi1rta, ezt az alkalmat inka1bb arra haszna1lna1m hogy az o3 elvi
lei1ra1sa1t egy konkre1t pe1lda1val illusztra1ljam. Nem a FORUM az
egyetlen fo1rum ugyanis amin Pellionisz drusza1mmal egyu2tt veszek
re1szt, e1s az a vitasti1lus (amely, mint tudjuk, maga a vitaember:-)
ami miatt e1n ta1vozok me1g a szerkeszto3 a1ltal "modera1lt" lista1kon
is kiu2tko2zik. Az ala1bbiakban ko2zlo2m, minden va1ltoztata1s e1s
kommenta1r ne1lku2l a "Neuron Digest" egy most zajlo1 vita1ja1nak ke1t
cikke1t. Az anyag sajnos nagyon hosszu1, kiza1ro1lag Hollo1si Jo1zsi
szeme1lyes kegyeke1nt keru2lt ki a FORUMra (de ha1t to2bbet nem fogok
i1rni u1gyhogy most aha1ny hu1sjegyem van mind beva1ltom). Sem a
vitaindi1to1 Pellionisz Andra1s, sem a kesztyu3t felvevo3 Michael
Arbib nem szorul bemutata1sra a FORUM olvaso1 elo3tt, hiszen jo1re1szt
me1g mindig matematikusok e1s sza1mi1to1ge1ptudo1sok olvassa1k.
Mindenkinek tova1bbi kellemes szo1rakoza1st, e1s Jo1zsinak me1gegyszer
ku2lo2n ko2szo2net az eddigeke1rt,
Sziasztok,
Kornai Andra1s
>From:  ("Neuron-Digest Moderator")
Newsgroups: comp.ai.neural-nets
Subject: Neuron Digest V9 #8 (discussion + jobs)
Date: 22 Feb 92 22:18:13 GMT
Reply-To: "Neuron-Request"  >
Organization: University of Pennsylvania
Neuron Digest Saturday, 22 Feb 1992
Volume 9 : Issue 8
Subject: Open letter to Dr. Sun-Ichi Amari
>From: Andras Pellionisz SL  >
Date: Wed, 29 Jan 92 17:38:04 -0800
[[ Editor's Note: I know many in the field regard Dr. Pellionisz as
holding controversial opinions. He and I have corresponded and I feel he
brings up some very valid points which should be the source of
substantive debate. The letter below is the result. I encourage
responses, either in support or refutation, to the following letter. The
main issue, that of intellectual priority and proper citation, affects
all of us in research and forms the foundation of the modern scientific
tradition. Dr. Pellionisz' secondary issue, international competition
versus cooperation, is also worthy of discussion, though I would request
that responses to Neuron Digest remain factual and near the subject of
neural networks. I also certainly hope that Dr. Amari responds to the
rather serious charges in an appropriate forum. -PM ]]
Dear Peter: according to our previous exchange, after long deliberation,
I put together the "Open letter to Amari". Given the fact that my
personal story is well in line with some global happenings, I trust that
you will find this contribution worthy of distribution
Andras
* "Tensor-Geometrical Approach to Neural Nets" in 1985 and 91*
or
OPEN LETTER TO DR. SUN-ICHI AMARI
by Andras J. Pellionisz
Dear Readers: Many of you may know that I pioneered a tensor- geometrical
approach to neural nets for over a decade, with dozens of publications in
this subject.
Many of you may have seen a recent paper on tensor-geometry of neural
nets (by Dr. Amari) as "opening a new fertile field of neural network
research" (in 1991!) WITHOUT referencing ONE of the pre- existing
pioneering studies. Dr. Amari did not even cite his own paper (1985), in
which he criticized my pioneering. This is unfair, especially since that
the majority of readers were uninitiated in tensor geometry in 85 and
thus his early "criticism" greatly hampered the unfolding of the tensor
geomery approach that he now takes. Unfortunately, Dr. Amari's paper
appeared in a Journal in which he is a chief editor. Therefore, I am
turning directly to you, with the copy of my letter (sent to Dr. Amari
21st Oct. 1991, no response to date).
There may be two issues involved. Obviously, we are entering an era which
will be characterized by fierce competition in R&D World- wide,
especially between US, Japan and Europe. The question of protocol of fair
competition in such a complex endeavor may be too nascent or too
overwhelming for me to address.
The costliness of pioneering and fairness to long-existing standards of
protocol in academia, acknowledgement of such initiatives, is a painful
and personal enough problem for me to have to shoulder.
===========================================
Dear Dr. Amari:
Thank you for your response to my E-mail sent to you regarding your paper
in the September issue (1991) of "Neural Networks", entitled "Dualistic
geometry of the manifold of higher-order neurons".
You offered two interpretations why you featured a Geometrical Approach
in 1991 as "opening a new fertile field of neural network research". One
can see two explanations why you wrote your paper without even mentioning
any of my many publications, for a decade prior to yours, or without even
mentioning your own paper (with Arbib in which you criticized in 1985 my
geometrical- tensorial approach that I took since 1980). I feel that one
cannot accept both interpretations at the same time, since they
contradict one another. Thus, I feel compelled to make a choice.
The opening (2nd and 3rd) paragraphs of your letter say: "As you know
very well, we criticized your idea of tensorial approach in our... paper
with M.Arbib. The point is that, although the tensorial approach is
welcome, it is too restrictive to think that the brain function is merely
a transformation between contravariant vectors and covariant vectors;
even if we use linear approximations, the transformation should be free
of the positivity and symmetry. As you may understand these two are the
essential restrictions of covariant-contravariant transformations. ...You
have interests in analyzing a general but single neural network. Of
course this is very important. However, what I am interested in is to
know a geometrical structures of a set of neural networks (in other
words, a set of brains). This is a new object of research."
THIS FIRST INTERPRETATION, that you could have easily included to your
1991 paper, clearly features your work as a GENERALIZATION of my
decade-old geometrical initiative, which you deem "too restrictive". I
am happy that you still clearly detect some general features of my prior
work, which you describes as targeting a "single neural network", while
yours as being concerned with a "set of neural networks". Still, it is a
fact that my work was never restricted to e.g. a SINGLE cerebellum, but
was a geometrical representation of the total "set of all cerebella", not
even restricted to any single species (but, in full generality, the
metric tensor of the spacetime geometry). Thus the characterization of
your work as more general appears unsupported by your letter. However,
even if your argument were fully supported, in a generalization of
earlier studies an author would be expected to make references, according
to standard protocol, to prior work which is being generalized (as my
"too restrictive" studies preceeded yours by a decade).
In fact, you (implicitly) appear to accept this point by saying (later in
your letter): "Indeed, when I wrote that paper, I thought to refer to
your paper". Unfortunately, instead of doing so, you continue by offering
a SECOND ALTERNATIVE INTERPRETATION of your omission of any reference to
my work, by saying: "But if I did so, I could only state that it is
nothing to do with this new approach".
Regrettably, I find that the two interpretations are incompatible that
(1) your work is a GENERALIZATION of mine (2) your geometrical aproach
has NOTHING TO DO with the geometrical approach that I initiated.
Since I have just returned from a visit to Germany (a country that
awarded to me the Alexander von Humboldt Prize honoring my geometrical
approach to brain theory) I know that many in Germany as well as in the
US are curious to see how THEIR INTERPRETATION of similarities of the two
tensor-geometrical approaches compares to Amari's and/or Pellionisz's
interpretation.
I can not run the risk of trying to slap into the face of the audience
two diametrically opposing arguments (when they will press me requiring
comparisons of your metric tensors used in 1991 and those that I used
since 1980). On my part, I will therefore take the less offensive
interpretation from those you offered, which claims that your geometrical
approach is in some ways more general than my geometrical approach a
decade before. As for you, I will leave it to you how you compare your
approach to mine, if you become pressed by anyone to substantiate your
claim over the comparison.
I maintain the position proposed in my original letter, that it might be
useful if such a public comparison is offered by you for the record at
the earliest occasion of your choice. For now, I shall remain most
cooperative to find ways to make sure that appropriate credit is given to
my decade-old pioneering efforts (however "restrictive" you label the
early papers and whether or not you have read any of those that I wrote
since1982, the date of manuscript of your 1985 critique). At this time,
I would like to refer to the wide selection of options taken by workers
in the past in similar situations.
Since by December 7, 1991, I will have made a strong public impact by
statements on this issue, I would most appreciate if during the coming
week or two you could indicate (which I have no reason to doubt at this
time) your willingness to credit my costly pioneering efforts in some
appropriate fashion. As you so well know yourself, a geometrical
approach to brain theory is still not automatically taken by workers in
1991, and certainly was rather costly to me to initiate more than a
decade ago, and to uphold, expand, experimentally prove in neuroscience,
and firmly establish in neural net theory in spite of criticisms.
Sincerely:
Dr. Andras J. Pellionisz
------------------------------
End of Neuron Digest [Volume 9 Issue 8]
***************************************
>From:  ("Neuron-Digest Moderator")
Newsgroups: comp.ai.neural-nets
Subject: Neuron Digest V9 #9 (discussion, jobs, misc)
Date: 2 Mar 92 23:23:58 GMT
Reply-To: "Neuron-Request"  >
Distribution: world
Organization: University of Pennsylvania
Neuron Digest Monday, 2 Mar 1992
Volume 9 : Issue 9
------------------------------
Subject: Reply to Pellionisz' "Open Letter"
>From: "Michael Arbib"  >
Date: Tue, 25 Feb 92 13:59:15 -0800
[[ Editor's Note: Here is another response. I appreciate the candor and
encourage others to express their opinion in a reasoned and supported
fashion. While I cannot comment on the correctness of the points either
in the original "open letter" or the various responses due to lack of
appropriate background, I am encouraged by the debate itself as process
of public education. -PM ]]
One of my colleagues sent me a copy of the letter by A. Pellionisz
complaining that Amari had not cited his earlier papers on applying
tensor analysis. Since my reply may be of general interest, I reproduce
it here:
"Amari had sent me the original letter, and we had agreed it was a
KINDNESS to Pellionisz not to refer to his earlier work, since in doing
so Amari would have had to summarize our 1985 argument showing that
Pellionisz had misunderstood the mathematics of tensor analysis. Anyway,
the work of Amari is NOT a generalization (why generalize a flawed
theory?!) but is a totally different application. For Pellionisz, the
tensors are the inputs and outputs to a single NN. For Amari (applying
his work of many years on information geometry) the whole NN is an
element of the Riemannian space on which tensors are defined, and the
metric on that space is used as an information measure to guide inference
of network parameters to find a NN meeting specified criteria. My only
criticism of Amari's paper is that it relies too much on his previous
publications directed to statisticians, and so will be very hard for NN
workers to read. Finally, note that tensor analysis is a powerful branch
of mathematics with many applications. The idea of applying it to NNs
does not need citation any more than does say the use of linear algebra.
But if one makes use of a specific technique in a way close to the work
of others, then full citation is appropriate. The latter case does NOT
apply here."
Let me simply add that the Japan-bashing in Pellionisz's letter is both
distasteful and (as I need hardly add) totally without foundation. It is
Professor Amari, not Dr. Pellionisz, who deserves a public apology.
Michael Arbib
Center for Neural Engineering
University of Southern California
Los Angeles, CA 90089-2520
USA
|
|
