----- Original Message -----
From: "Shane Legg" <[EMAIL PROTECTED]>
> I think my reply to this is similar in nature to Ben's (however I think
> Ben's example of a push down automaton is a bit misleading as it's
> really the abilty to carry state between system cycles not during a
> cycle of that is important)
>
> So, if I is the input space and O the output space then you are
> claiming that an AI which is simply a function F: I -> O isn't
> going to be able to adapt. Clearly this is true.
Yes, this is what I mean.
> However there is no reason why we can't carry state. If S is
> the state space of our system then define F: I x S -> O x S
> where the output state is fed back into the system on the next
> cycle. Or in explicit functional form something like
>
> ( o_{n+1}, s_{n+1} ) := F( i_n, s_n )
>
> Would you consider such a system to not be computation is the
> theoretical sense?
See my replies to Ben. As soon as the final answer (not intermidiate
answer) depends on internal state, we are not talking about the same Turing
Machine anymore. Of course you can build a thoery in this way, but it is
already not the current "thoery of computation".
Pei
> Cheers
> Shane
>
> -------
> To unsubscribe, change your address, or temporarily deactivate your
subscription,
> please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
>
-------
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
