On Thu, Nov 27, 2008 at 02:40:04PM -0500, Abram Demski wrote:
> Russel,
> Hmm, can't we simply turn any coding into a prefix-free-coding by
> prefacing each code for a GTM with a number of 1s indicating the
> length of the following description, and then a 0 signaling the
> beginning of the actual description? I am not especially familiar with
> the prefix issue, so please forgive me if I am wrong...

Sure - but you also need to change the machine to recognise your code.

> Also, I do not understand why there would be reason to suspect that
> the probability distribution, once properly defined, would turn out to
> be equivalent to the S-L prior. GTMs can formally represent more
> things than TMs, so why would those things not end up in the
> probability distribution?
> --Abram Demski

Its been a while since I read Schmidhuber's papers, but I thought he
was talking about machines that continuosly updated their output, but
would eventually converge (ie for each bit i of the output, there was
a time t_i after which that bit would not change).

This seems to be a restriction on the notion of Turing machine to me,
but not as restrictive as a prefix machine.


A/Prof Russell Standish                  Phone 0425 253119 (mobile)
UNSW SYDNEY 2052                         [EMAIL PROTECTED]
Australia                                http://www.hpcoders.com.au

You received this message because you are subscribed to the Google Groups 
"Everything List" group.
To post to this group, send email to [EMAIL PROTECTED]
To unsubscribe from this group, send email to [EMAIL PROTECTED]
For more options, visit this group at 

Reply via email to