e=r-p

[From Shannon Williams (9614.03:30)]

Martin Taylor 960111 14:55--

I don't understand the leap from trainable or self-teaching networks to

       such that we can look at the cumulative effect of
       this mapping and describe it as e = r - p.

Networks give you an input/output mappings. Modifiable networks give you
the capacity to learn input/output mappings. The cummulative effect of
these mappings allows an external observer to describe an organism's
behavior as e=r-p. It's a very simple concept.

Maybe you could figure out a question that identifies what you don't
understand. Or sketch what you think that I am saying, and point out its
logic flaws.

------
       2) If e = r - p describes the output of a group of neurons, then
       then HPCT, or some form of it must be true. Because without HPCT,
       there is no method of explaining how new loops form.

If you insist that all control loops are operating
in parallel, connected directly to sensory input and to the muscles, then
the argument from existence should be enough to say that there is a method
whereby those loops came to exist.

You are right that the way that I am visualizing the control loop explains
not only the control loops' existance but their origin. But I am not
visualizing parallel loops. If the loops were all parallel, we would never
experience conflict.

       3) If I am going to model behavior using a neural network, I can
       simulate the evolution of behavior using the visualization in #1.
       But I can't if I am using the visualization in #2.

Whyever not?

Draw a sketch outlining how PCT models the evolution of behavior. I want
to see each little stage of the evolution. Show me this, and I will answer
your question. (No perhapsial handwaving, please).

···

------------------------------------------------------------------------

[Martin Taylor 960111 17:10]

I must be really on a different wavelength from you,

I agree.

-Shannon