Re: face-selective region


Curt Welch wrote:

H does have his associative memory as the 2nd major part of his
hierarchical scheme. As he mentioned, the power of the overall system
comes from having utterly huge amounts of such memory. This of course
deals with the so-called "common-sense" problem. How can a human
successfully function in the range of environments it functions in, and
escape the usual brittleness problem of most AIs? The primary answer is
to have a lot of memory with stores for many different real-world
situations, skills, etc. This is part of the solution, but the weak
part of H's model is tying everything together.

Yeah, he's got a clear understanding of how associative memory is able to
tell us the "answer" for any new situation. It picks the "memory" which
most closely matches the current situation. He just didn't answer how the
system knows _what_ to do in the situation.



No doubt, for a given situation, there will be 100s or 1000s of
simultaneous and parallel outputs from various parts of the associative
memory systems. The question is how to boil this down to get one final
answer, and one behavior out of this, rather than 1000s.

This is possibly where ideas of self-organization + complexity might
come in, as indicated in the other thread regards Andreason's book.
Since all of these areas are interconnected via bidirectional pathways,
all of these signals will in effect "bounce off" of each other, and
affect each other. In an SOS, this would result in some coherent
activity emerging out of the chaos. But who knows.

.............



Also, as you indicate, there does need to be some sort of goal-system
overlaid on the rest of it which indicates which items to store and
which items to ignore. Towards the end of the book, H does talk about
applications for his model, but these are somewhat limited apps, such
as air-traffic control, so the goals are really set ahead of time, and
the domain of the learning situation limited, by the external user.

Yeah, I'm in that part of the book now. He tends to focus on the
perception side of the problem and talks about how a memory prediction
system would correctly understand what it was seeing. And he talks about
the obvious advantage of being able to watch a video screen and understand
what you were looking at. But he never answers the question of how you
train the system to produce the behavior you want to to produce - such as
calling the police when you see a crime. At best, he makes reference to
how you can tech it by repetitive example but that's not enough to explain
why the machine would want to mimic your examples instead of just punching
you in the face.



Edelman discusses the idea of the brain value system in his book A
Universe of Consciousness. Basically, it's a small set of subcortical
centers that send a thin net of fibers which fan out to all areas of
the cortex and other areas of brain. There are several centers and
neurotransmittter types. Locus coereleus and noradrenaline. Raphe
nucleus and serotonin. Plus some dopaminergic, cholinergic and
histaminergic nuclei.

Regards function ... neurons in these nuclei fire when something
inmportant or salient occurs, and then via the wide-spread fiber
networks cause the diffuse release of the neurotransmitters, which
"modulate" activity in billions of other neurons. Thus, there is a
large amplification of effect, a few 1000s of neurons modulate
wide-ranging neural activity and also synaptic plasticity.

Further .... these sites are important targets of pharmacological
intervention, since small changes in function of these cells can have
global effects on brain operation.... these signals carry information
about ongoing behavioral state [sleep, waking, grooming, etc], as well
as sudden occurrence of important events [novel + painful stimuli,
etc]. Some neurons fire tonically when the animal is awake, and others
produce bursts of activity when something important occurs.

This sort of thing would be pretty easy to superimpose onto a Hawkins'
like model.

.............

Yeah, I get this. Inverse hierarchy. Divergence of signals going down
the motor hierarchy, analogous to convergence of signals going up the
snesory hierarchy. That's very short-term. You still need a good way to
deal with longer-term activity. Even going around the entire outer
loops [ie, internal comps + external behavior], the loop activity is
very fast, under a second or so. You still need a good way to direct
actions over the course of many seconds, and even minutes.

With feedback systems, one thing leads to another, which leads to
another, on and on, so everything is done on the context of the
previous, but you still need some long-term directional control, else
you'd simply be responding constantly to immediate contingencies.
Brooks' reactiveness extended a bit with STM. It's not clear to me from
H's model how you get more long-term planning into the mix.

Yeah, and reinforcement learning is long term memory. So it's the
reinforcement learning system that answers how you can have a memory that
goes back to yesterday. It answers how you can set a goal on Monday to do
your food shopping on Friday after work and actually remember to do it.

The details of you you implement it to allow this to happen is not obvious,
but at least it gives one answer to the question of how and why it happens.

And reinforcement learning is a long term feedback loop.



Yeah, the information stored in the associative memory is the result of
the reinforcement learning processes.


........


Reading some other stuff [I'll start another thread on this, regards
hierarchy and dynamics, from book called The Primate Visual System, ed
Kaas + Collins, 2004 .... good book, you should take a look], the idea
of the HC at the top of the hierarchy probably comes from van Essen's
diagrams of the 30+ visual areas, with HC on top.

However, I think H misinterpreted this. The diagram shows the HC on
top, because essentially the only visual area it connects to is ER
[enterorhinal], which is shown on the diagram as being atop the
hierarchy of visual areas. The HC is not shown to connect with any of
the 30 other visual areas. However, if true, to me this means the main
control of STM is at the the top, rather than the HC being some kind of
"executive" module.

IOW, I interpret the system as the 30+ areas mainly being hierarchical
filters, and STM doesn't factor in significantly until later [ER level,
which is up approx 13 levels into the hierarchy].

I see most of H's idea of a memory/predictive system to be what creates STM
effects. If you have a system that can recognize a cat, and predict that
it's still there, even after you turn your back to it, then that is a STM
memory system that allows you to "know" there's still a cat there 2 seconds
after you can no longer see it.



Yeah, I miswrote that. What I meant to say is the HC factors into
conversion of STM into LTM, and if you interpret the van Essen visual
hierarchy in this manner, since HC connects only at the top to ER
cortex, and not to the other 30+ areas distributed over many levels,
then this would indicate that the topmost levels are the main place
where LTM generation would occur. This would indicate there is less
learning taking place at lower levels, and therefore these lower levels
would mainly be involved in filtering, feedback, prediction, and other
real-time short-term activities, rather than plasticity.



It's just the predictive memory system
that's in effect saying, "I expect with high probability to see more
"cat-patterns" in the sensory data soon". That's basically the system he's
talking about. It's a temporally sensitive pattern matching hardware which
picks up pattern clues not just from the present, but from the recent past
as well. It knows there were cat-patterns in the data 5 seconds ago so
it's predicting there's a higher probability to see more cat-patterns right
now than to see elephant-patterns. This is what allows the associate
memory to see only a small corner of the ear of the cat and quickly
classify it as cat-ear because the odds of that pattern being cat-ear
instead of something else is much higher because of the fact it saw the
rest of the cat 5 seconds ago.

For the classification system to use knowledge of what happened in the
recent past to make more accurate current classifications it must have some
form of short term memory in it.



Yes, there is continuous activity going on in the various feedback
loops at the lower levels.

..................



Well, in real brains, we have parallel pathways from subcortical
centers including the amygdala and other limbic areas which factor in
emotions and other goals/values. Missing from H.

Yeah, he makes clear reference that an actual human brain is much more than
just the cortex and gives connections to the lower brain like you mention
as examples. To create a human like robot, with emotions, you would have
to spend all the time to reverse engineer all that lower brain stuff.



As indicated above, regards Edelman's book, much of this info is
already present in the neuroscience literature.

..... [you might also look at the response I made a couple of days back
to the first half of your post from a day or so before that] ....




I of
course agree in principle with that, however, the prime cause of emotions
in humans is the value system created by the reinforcement learning
algorithm. He thinks he could build useful systems without emotions, but I
think that without a value system, you can't build anything very useful at
all because you won't be able to train it to do what you want it to do.
Though how we express our emotions and how they change from day to day
might be heavily regulated by lower brain functions, the need for basic
emotions which is the value system created by reinforcement learning, is a
requirement for AI.

The nice thing about the H framework is that it's easy to add parallel
systems that can have totally different architectures [as the
subcortical and limbic areas have], and wire them [both as inputs and
outputs] into appropriate points in the hierachical framework.

Eg, sample ongoing activity in general, do some calculations, and then
feed either excitatory or inhibitory inputs back into the hierarchy at
strategic points. Such pathways are found in the real brain, but not in
H's current model.

Yeah, but he knows the brain is actually more complex and the book is only
an attempt to identify the correct top level framework so that the details
of the brain can be filled out in a top down fashion instead of the
bottom-up fashion most research on the brain has been done on. And as
such, I think he's on the right track and basically right about most of
what he says. He's just missing the reinforcement learning framework.

Yeah, my point was that, this is so because the overall connection
scheme is dictated by the DNA. Learning doesn't work in a vacuum. It
works in the context of a system highly-structured genetics and refined
by evolution.

Right.

--
Curt Welch http://CurtWelch.Com/
curt@xxxxxxxx http://NewsReader.Com/

.

Relevant Pages

  • Re: Syntax and robot behavior
    ... now because what I have to say below about reinforcement learning touches ... of the brain accessible only indirectly, ... entire neocortex is made up of the same fundamental hardware structure ... Yes, but a computer memory can, though structurally amorphous, ...
    (comp.robotics.misc)
  • Re: face-selective region
    ... you have to add a reinforcement learning system to map the ... current state (i.e., the stimulus signals), to behavior. ... H does have his associative memory as the 2nd major part of his ... Inverse hierarchy. ...
    (comp.ai.philosophy)
  • Re: Invariant Recognition, Grandmother Cell, and Memory Hierarchy
    ... >> This filtering and abstraction is probably mainly a feedforward ... >> probably has nothing whatsoever to do with memory, ... The hierarchy is anatomical, and is feedforward, ... > this is first routed through the "static" pathways in the brain. ...
    (comp.ai.philosophy)
  • Ive an odd feeling Ive read this before
    ... memory is a reliable tape recorder. ... feelings of familiarity simply should not exist. ... spanned a wide spectrum, including past lives, precognition, brain ... a professor of psychology at Southern Methodist ...
    (uk.philosophy.humanism)
  • Re: Memory is not infinite
    ... axons and dendrites in synapses in the brain. ... it appears the brain can't remember infinite things because it ... needs to scavenge old connections for new memories, and also, memory length ... The rest of the day-to-day memories ... ...
    (talk.origins)