[comp.ai] free will and errant gamma rays

silber@sbphy.ucsb.edu (04/20/89)

Even if one knows the architecture, program, and initial state of
some deterministic man/machine, one cannot with certainty predict
the sequence of machine states which it will traverse when executing
the program, BECAUSE it is not executing the program in a vacuum.
At any instant, an errant gamma ray may twiddle a bit here or there
and so on.  So, the choice one makes may be 'determined' locally by
the unperturbed locally-deterministic environment OR it may, by 'chance'
be determined by some event originating in a larger, possibly undeterministic
context.  (and even if the larger context (i.e. the distant nebula where
the gamma ray originates) is also deterministic, the lcoal system 
reacts to the gamma ray AS IF a free-will-choice were made)
So as far as man made a-i machines are concerned, maybe, at some point,
one might want to specifically include some physical random event
generator (a lump of radium or some such radioactivbe source) ?????????

ins_atge@jhunix.HCF.JHU.EDU (Thomas G Edwards) (04/22/89)

In article <1499@hub.ucsb.edu> silber@sbphy.ucsb.edu writes:
>So as far as man made a-i machines are concerned, maybe, at some point,
>one might want to specifically include some physical random event
>generator (a lump of radium or some such radioactivbe source) ?????????

I'd say that there are plenty of AI paradigms making great use of
random number generators!  When you train a neural-net, you usually
begin with small random weights between the neural units to break the
symetry of the network so the gradient descent process can change
every weight individually.

Boltzman machines (a kind of connectionist learning routine which
involes "simulated annealing," or slowly letting the network relax
into a low energy state by changing how fast a neural element can change
state) depend on random numbers, since neural elements have probabilities
of being on.

In genetic algorithms, random number generators are essential to
adding genetic novelty to the search space of the algorithms.

-Thomas Edwards