Re: virus: Re: neural nets

Alex Williams (thantos@decatl.alf.dec.com)
Sun, 5 Jan 1997 17:41:35 -0500 (EST)


> You seem to be confusing Turing machine with von Neumann machine. The
> computer on my desk is not a Turing machine any more than a neural
> net is a Turing machine. But a Turing machine can emulate both perfectly.

You are absolutely correct, and I fine myself 5000 Zorkmids for such
an extended brainfart. (Not that I think it matters at this point,
only we two are reading this and getting anything they care about out
of it. :)

> There isn't any symbolic understanding or comparison inside a Turing
> machine either then. Some patterns cause other patterns to be written
> to the tape.

Replace Turing by Von Neumann in every instance I've used it over the
course of this discussion for the past X days, except when I actually
meant Turing ... (Another discussion I'm in on another ML is
centering about Turing tests, the only reason I can figure for
brain-death of such magnitude.)

> Are you claiming that neural nets can't do computation, or that
> computation takes place at a higher level, or something else?

I'm suggesting that Von Neumann computational systems are inherently
more computationally flexible than NNet architectures because the
latter don't do `computation' as such by storing values in memory,
doing ongoing comparisons to state changes, etc. NNets take in
patterns and output patterns without `computation' going on between.
A sufficently large and complex NNet could map the set of all possible
memory states of a Von Neumann machine to all possible output states,
but I'd really have the Von Neumann box if I'm trying to fit into the
same room as my equipment and have it cost less than a medium-sized
country.

Even given the Mondo-Mega NNet that models an entire 4meg memory
Pentium from state to state, it can't model the exact same machine
with 5meg of memory. To do so requires an entirely new NNet with all
attendent learning time and physical expansion.

> Yes, thinking is an emergent act arising from the interactions of memes,
> or more specifically, from beliefs caused by memes. Why wouldn't memes
> that act on other memes alone still be memes?

I agree with you, but we've had discussions over whether or not memes
that don't exist within a given mind are memes (and you'll recall I'm
a heretic there, at least). I have to question everything once in a
while.