> > > That still doesn't mean that there's `computation' going on inside the
> > > NNet, just as there isn't really `planning' going on inside a
> > > spreading activation agent network. Certain things threshold at
> > > certain times and certain actions/behaviours result.
> >
> > You are using "computation" in a sense I don't recognize. What do
> > you mean by it?
>
> Computation in the symbolic sense; there isn't symbolic understanding
> or comparison going on inside a NNet structure, some patterns just get
> more weight than others, trickle down through the layers and finally
> render /this/ output pattern. A given NNet isn't a general-purpose
> computing device while a Turing machine is.
?????
I'm going to need some clarification on the first sentence in the last
paragraph.
Surely the comment about "no symbolic calculation in a neural network"
refers to the abstract data type, rather than the machine-implementation?
Even working at the abstract data-type level, that comment is inobvious.
I'm going to need to know how to reframe your clarification to obviate
the "symbolic calculation" from the "some patterns get more weight than
others...."
I have no problems with the last sentence.
//////////////////////////////////////////////////////////////////////////
/ Towards the conversion of data into information....
/
/ Kenneth Boyd
//////////////////////////////////////////////////////////////////////////