Re: Serious *Mistake* by Schmidthuber

From: Russell Standish <>
Date: Mon, 9 Sep 2002 09:49:58 +1000 (EST)

Interesting post. Unfortunately, I don't have enough time at present
to properly digest it or understand it.

I gather that your "rare events" are the ones of measure zero. In the
Schmidhuber ensemble, these events are never observed, and
consequently are ignored. Only finite length descriptions (ie the ones
with positive measure) are observable. Why do you think things like
the big bang, or inflation are of measure zero? It strikes me that
that these events are of rather low complexity, hence have fairly high


Osher Doctorow wrote:
> From: Osher Doctorow, Fri. Sept. 6, 2002 11:45AM
> I have read about half of J. Schmidthuber's *A computer scientist's view of
> life, the universe, and everything,* (1997), and he has interesting ideas
> and clarity of presentation, but I have to disagree with him on a number of
> places where he uses conditional probability including his section
> Generalization and Learning. I hasten to add that I do not view
> alternative theories as *wrong* but as competing and that they should almost
> all survive for competition, motivation, and also because many of them turn
> out to have useful contributions long after they have been regarded as
> *discredited*.
> Schmidthuber (S for short) concludes that generalization is impossible in
> general by using a proof based on conditional probability, and similarly he
> concludes that the learner's life in general is limited by also a
> conditional probability proof. Most readers will undoubtedly stare at this
> statement in bewilderment, since as far as they know nothing is wrong with
> conditional probability.

... stuff omitted for brevity ...

A/Prof Russell Standish Director
High Performance Computing Support Unit, Phone 9385 6967, 8308 3119 (mobile)
UNSW SYDNEY 2052 Fax 9385 6965, 0425 253119 (")
Room 2075, Red Centre
            International prefix +612, Interstate prefix 02
Received on Sun Sep 08 2002 - 16:58:29 PDT

This archive was generated by hypermail 2.3.0 : Fri Feb 16 2018 - 13:20:07 PST