Re: Neural netss (was Re: death of the mind.)

From: Alex Green (dralexgreen_at_yahoo.co.uk)
Date: 08/31/04 

Date: 31 Aug 2004 04:02:02 -0700

Wolf Kirchmeir <wwolfkir@sympatico.ca> wrote in message news:<_VGXc.30806$DG.1600198@news20.bellglobal.com>...
> Eray Ozkural exa wrote:
>
> [...]
> >
> > Here is a question for you, Wolf. What does the "face recognition"
> > circuitry in your brain accomplish? If it does not contain reference
> > states, what does it contain then?
>
> As I understand it, the "face recognition module" responds to specific
> inputs from the otber areas of the VC/etc, which in turn respond to
> inputs from the retina (which, as you know, organises the visual data
> transmitted by the rods/cones). The "reference state" that you and
> others refer to is as I understand it the organisation of the NNs in the
> face recognition module. OK, now what? I see little utility in talking
> about it that way. The abstract terminology may help if you want to
> mimic the operation of the VC in a digital computer, since it suggests
> architecture, but it doesn't help much otherwise that I can see.

Once it is agreed that the brain contains a reference state we can
compare this state with the results of experiments in cognitive
psychology. It turns out that when subjects report the content of what
is called 'perception' this corresponds to the content of the
percept/reference state in the brain. This also occurs in dreams (when
subjects are woken and asked about their dreams the content
corresponds to fMRI data).

This gives us a problem. When you look around you the content of your
experience is a set of brain activity based on sense data, not a
direct contact between some imaginary point eye and the mostly vacuum
of the world. But we all think of our experience in terms of geometry,
in fact it IS geometry. It is like a view of the world from a point
eye. How can a set of brain activity have the geometric form of
experience?

>
> The phrase may in fact mislead, since it implies a comparison (and the
> comparison has been explicitly invoked by some contributors to this
> thread.) But I don't see any comparison happening - there is AFAIK no
> "comparator module" that takes input from the "perception module" and
> the "face recognition module" and outputs "Yup, that's Johnny."

In the cerebellum the output signals for motor control are comparator
outputs.

Wherever we see feedback in a biological system we should suspect a
comparison is occurring. The way the entire percept in the cortex
switches in binocular rivalry would be expected from the feedback from
cortex to LGN.

> The fact
> is that information about edges, etc is produced in the retinal layer,
> that this information passes to various NNs whose output goes to other
> NNs, etc until the final output is "That's Johnny." At each layer, the
> information is reorganised - that is, the inputs to the next layer have
> a different pattern. Note that the face recognition module is not as
> simple as the name impies - some people who have had damage in that area
> can still tell they are looking at a face, they just can't tell who it
> is. Others can't even tell they are looking at a face. Since the damage
> is to the NN, the "reference state" can only be the organisation of the
> NN, as I said above. Again, now what? The organisation of the NN
> determines how it operates, is all. Calling it a reference state doesn't
> help us understand how it's organised.

In binocular rivalry the entire percept switches dramatically, it is
not all a fuzzy process leading from input to output. Calling it a
reference state is essential to distinguish it from this other, fuzzy
state you are describing. The brain does indeed seem to create a model
of the world.

> Sidebar: The closest computer analog I can see to what happens is bit
> masking. However, in a computer, the bit mask is imported from storage -
> there is no similar event in the brain that I can see. The NN itself
> masks or filters the input; it doesn't import a mask.

Binocular rivalry shows that the percept processed from incoming data
and probably stored data (there are practice effects in cognitive
rivalries) can mask data that does not fit the percept.

>
> The reason I keep talking about brain physiology as I understand it is
> that I've never been happy with abstract models that ignore the messy
> details. "Reference state" is such a concept, since it applies to
> devices that function differently than NNs.

Interacting NN's such as modules in the cortex or cortex and LGN could
easily create the required operations.

> Sure, it's very satisfying
> to recognise some abstract identity (eg, abstractly considered, the
> state of a network can be thought of as stored information), but the
> messy details keep interfering with insight (eg, when the network
> changes state, some or all of the previous information is lost, unlike
> information stored by other means.) Abstract models are useful - they
> obviously help in constructing devices that work-alike some observed
> brain function/system behaviour/etc.
>
> > If you can answer this question, then I have a harder followup. What
> > do you think a neural network, be it natural or artificial,
> > accomplishes? What does it do? How is its operation correlated to the
> > environment, say, during simple categorization (of audio or images)?
>
> It filters and organises input data. That is, given a mess of inputs,
> the NN passes some and blocks others. The output may be "pattern
> recognition", or input to another NN. The following description will
> show what I understand happens: Given an NN that's been trained to
> "recognise the letter A". Input visual data of the letter B. Some of
> that data will "pass", that is, activate some connections as the data
> flows through the NN (eg, the centre horizontal bar of the B.) Most will
> not. The NN will respond (output "Letter A") if enough of the
> connections within it are activated and not otherwise. The "reference
> state" is the organisation of the connections. Eg, a certain group
> inputs are connected to one element, some of the same inputs are
> connected to another, and some to a third. If all inputs are on, all
> three elements will fire; otherwise only one, or none. NB that my
> description assumes a layered architecture. A good example of what I
> envision is the mammalian retina, which is a neural network of exquisite
> precision. IMO the organisation of the retinal NN is repeated throughout
> the brain.
>
> The "correlation to the environment" is a phrase that I don't find very
> meaningful. There are organised inputs from the sensors. If the sensors
> provide inputs such that the "A-recognition NN" responds, then the
> system has "seen" the letter A.

This is OK at the level of the processing functions of NN's and I
would agree with the analysis.

>
> And categorisation of audio or images is _not_ simple. Anyone who has
> tried to write a categorisation tree to distinguish between CAT and DOG
> should know that. I've doodled some myself, and I've found that at every
> level there are assumptions about what the subcategory "means", ie, each
> node hides another tree. Add to that the problem of recognising a CAT
> or DOG from variable visual data, and the problem is seen to be
> horrendously complex. It's no accident that optical NNs have barely been
> ablt to recognise letters, and even those not reliably. IMO, the central
> problem of NNs is not their general organisation or properties, it's the
> nasty little details of how to actually connect the actual elements.
> Small differences in connection topology may have large effects on the
> NNs operation; and those effects aren't easily predictable. It's much
> easier to refer to "emergent properties" than to design a device that
> will display those emergent properties.
>

I suspect that current simulated NN's do not have adequate or
appropriate functions to enrich the analysis of the data. Although the
brain is a topographic processor it also contains analysis modules,
some as small as sets of interneurones. The incoming data stream is
enriched with analyses of many different types, also arranged
topographically and also capable of involvement in the neural net.

However, this still leaves us with another problem. How can our
experience be our own neurone activity, the activity that is based on
the percept? This can only be answered by introducing scientific
theories that go beyond information processing.

Best Wishes

Alex Green

Relevant Pages

  • Neural netss (was Re: death of the mind.)
    ... If it does not contain reference ... the "face recognition module" responds to specific ... others refer to is as I understand it the organisation of the NNs in the ... there is no similar event in the brain that I can see. ...
    (sci.cognitive)
  • Re: Why Software Is Bad and What We Can Do to Fix It
    ... > Forgetting is due to a slow decay of synaptic strength or to some ... Yes, it is obvious that many neurons fire at the same time, but the rest ... > occurring in the brain at any one time, i.e., synchronously. ... same time without reference to the timing of the events, ...
    (comp.object)
  • Re: Origin of the word "Creationism"
    ... reference this fact from 20 different sources at the drop of a hat... ... evolution created the brain and a faculty ... which invented God. ...
    (talk.origins)
  • Re: Origin of the word "Creationism"
    ... Produce the 20 reference sources or shut up. ... evolution created the brain and a faculty ... How do you diagnose brain damage, how do you determine that your own brain ...
    (talk.origins)
  • Re: [OT] TV Series ID
    ... (I'm actually not completely sure that recognition ... Here's an example of recognition humor: there's a story (it might be ... For that one, you need to recognize the form of the joke, and remember ... I would *love* to see brain imaging done on people viewing different ...
    (rec.arts.sf.composition)