In <01bcefc9$33b20160$e67a61ce at asdf> "ray scanlon" <rscanlon at wsg.net> writes:
>Neil Rickert <rickert at cs.niu.edu> wrote in article
><64a8qu$abu at ux.cs.niu.edu>...
>> In <01bceec8$7cb77900$fd7a61ce at asdf> "ray scanlon" <rscanlon at wsg.net>
>writes:
>> >Connectionists look to the brain, the net of neuromimes is their
>> >paradigm.
>> But the tools the connectionists have are too weak, given the
>> magnitude and complexity of the task.
>Not in my opinion.
Go at it, and prove me wrong.
>Are we looking to explain awareness?
I assume so.
> Is it our goal to construct a
>brain that has awareness inherent in its architecture and thus explain
>the world of intension in extensional words? You said that you don't
>believe this possible so let me just put it aside.
I don't recall saying any such thing. I believe it is possible in
principle, but the practical difficulties will be so large that I
doubt they will be overcome.
> What remains? Are we
>confusing a multitude of neurons with complexity?
When the problem is posed in terms of the detailed structure of the
neural net, the complexity is enormous. From a top down view --
analyze the problem, rather then the biological hardware -- it does
not look as complex. But you are insisting on the bottom up
approach.
>What is needed is the ability to generalize, the ability to clear off
>some trees so we may have a clear view of the forest.
But I think you have made it very difficult to generalize by
insisting on a bottom up neural net methodology.
> Those jellyfish
>that have advanced to the stage where they have interneurons between
>the sensory neurons and the motor neurons do not seem to pose much of a
>problem to being simulated with a neural net. Yet the whole story is
>there.
It is not at all clear that the jellyfish neural net is comparable to
the vertebrate neural net. The jellyfish has to solve very different
kinds of problems.