Re: How much intelligence?

Curt believes in talking rocks. Behaviorists believe in Curt.

Curt believes in things that have hardware that enables them to talk.

The assumption is that if we learn the same way dogs learn, then dogs should
have the same language skills we have. But they don't. So the conclusion
is that we must have special language hardware in our brains to explain our
advanced language skills (which is obvious), which must use a different
system than reinforcement for learning (which is not obvious).

I agree about the hardware. I believe I remember reading in a book I
borrowed from a professor (Fundamentals of Neuropsychology) something
about a section of the brain that (supposedly?) gives us speech
abilities. I may be wrong though. Maybe I'm confusing that with the one
that gives us our sense of time.

I'm not so sure I agree with the assumption that humans use a different
reinforcement system for learning. I haven't seen any evidence for this
in the articles I've read about learning experiments (i.e., the ones
that come up periodically on Slashdot).

Do you think a good model that does what I mentioned in my first post
would be structured anything like the human brain is structured?

But, associative learning is emotional, where an input causes a
positive or negative feeling by virtue of its direct or indirect association
with pleasure or pain, and that feeling causes us to approach or flee the cause
of the input. It's all about what is good or bad, as directly experienced, and
what is associated with those good or bad things, as directly experienced. We
still operate this way, but not exclusively.

I think I have to partially disagree with this. I don't think
associative learning is emotional; rather, it is based on stimulus - or
is it not? By emotions do you mean stimulus?

I also think we do choose what we say based on our current situations,
our what we've learned in the past, and our emotions at the time. What
is missing? Do you disagree?

When we speak of natural language, there is no emotion necessarily involved. We
can say, "There are seven red bananas on the counter," and not care, while
noting the fact.

I agree with you that there is (often) no emotion involved in speaking
natural language. However, I would have to argue emotion is involved
some of the time. I would also argue that our choice of words is based
on pattern recognition (what we know; from sentences and phrases that
we hear throughout our life). It's easy to see the difference between
the way educated and non-educated individuals talk. Educated people
almost always use better grammar, better spelling, and they have much
better choice of words because of their large vocabularies. This is one
thing that makes me lean toward the idea that language is a product of
our experience. Do you agree?

Language is not emotional persay, and not concrete. It's an abstraction.

I agree, this is true. How do you personally think a person chooses
their words when they say things? We obviously choose words that most
closely match the concept we have in our minds and want to portray. And
we can clearly say this: we must have the concept in our minds before
we can choose the words to portray this concept. So maybe our
short-term memory goes out and "queries" our long-term memory for the
concept which is best associated with the concept. What do you think?

In order to learn
language, the first thing that is necessary is the ability to maintain an
abstraction, a variable that refers to something, rather than simply
associating feelings with its presence or absence.

Then, as Lester points out, there are considerations of syntax and grammar
...
manipulate using the syntactical rules of the language.

I would think these abstractions are maintained in short-term memory.

It's a different configuration that
allows us to formulate representations of realities which can then be
manipulated according to logical symbolic rules, which are represented by the
same mechanism. Each such representation acts as a symbol.

Again, I would think that this is where short-term memory comes in.
These representations of reality are represented in long-term memory,
and then they are pulled in and represented in short-term memory. Do
you agree?

Logic - do you think this is done in the human mind via some form of
set theory?

So, chadmaster, above you will find a typical anti-behaviorism argument.
As I said, I seem to be part of a minority.

And I agree with you on many points. I also agree with Lester and Tony
and many others. And like I said before, I do think that the best
approach to AI is a bottom-up approach that is based on biolical
aspects. If you want to model something biological, then your model
should model biological things (e.g., the functionality of a neuron).

I think a big difference, if not THE difference, between our minds and
animal minds is the hardware. Does anyone disagree?

It would have to be able to access multiple existing associations

Liz, what do you mean by "multiple existing associations?"

You honestly have some very good and interesting points there. Those
are things I'll definitely be thinking about.

Curt, with what Liz said about mimicing behavior, do you think this is
can be explained using hte behaviorist approach?


(everyone)

You do have to admit that there are vast similarities between the way
animals and humans learn. Pattern recognition is common to both, as is
punishment and reward. I don't think the difference is really HOW we
learn, but rather how we do it.

So overall, without consideration of complexity, does anyone think that
such a task is entirely impossible using a computer model?

.

Relevant Pages

  • Re: VMS
    ... because it was tailored to the platform rather than the language. ... > best machine architecture (PDP-11, VAX, Alpha) and the best software. ... the hardware really didn't matter. ... applications and in the IT world bus speed is more important than ALU ...
    (comp.object)
  • Re: Cells compared to Flow-Based Programming
    ... Given that it's not even possible to proof hardware, ... a language with imperative features is inherently ... of the acquired company that they don't like. ...
    (comp.lang.lisp)
  • Re: a dozen cpus on a chip
    ... No nontrivial language can ever be proven to be imposible to crash. ... compilers still available which implement ISO M2. ... It is a common misconception that Lisp is always interpretted. ... various X86 machines the hardware does exist that could allow the OS ...
    (sci.electronics.design)
  • Re: How much intelligence?
    ... Curt believes in things that have hardware that enables them to talk. ... have the same language skills we have. ... These representations of reality are represented in long-term memory, ...
    (comp.ai.philosophy)
  • Re: Another transputer-inspired language?
    ... describe permanent ASIC/VLSI hardware devices. ... only support Verilog & VHDL. ... shrinking but the no of FPGA starts is exploding due to lowish NRE ... When I suggest the V++ language be modeled after ...
    (comp.sys.transputer)