Re: [agi] Hutter - A fundamental misdirection?
In short, instead of a pot of neurons, we might instead have a pot of
dozens of types of
neurons that each have their own complex rules regarding what other types
of neurons they
can connect to, and how they process information...
...there is plenty of evidence (from the slowness of evolution, the large
number (~200)
of neuron types, etc.), that it is many-layered and quite complex...
The disconnect between the low-level neural hardware and the implementation
of algorithms that build conceptual spaces via dimensionality
reduction--which generally ignore facts such as the existence of different
types of neurons, the apparently hierarchical organization of neocortex,
etc.--seems significant. Have there been attempts to develop computational
models capable of LSA-style feats (e.g., constructing a vector space in
which words with similar meanings tend to be relatively close to each other)
that take into account basic facts about how neurons actually operate
(ideally in a more sophisticated way than the nodes of early connectionist
networks which, as we now know, are not particularly neuron-like at all)? If
so, I would love to know about them.
On Tue, Jun 29, 2010 at 3:02 PM, Ian Parker ianpark...@gmail.com wrote:
The paper seems very similar in principle to LSA. What you need for a
concept vector (or position) is the application of LSA followed by K-Means
which will give you your concept clusters.
I would not knock Hutter too much. After all LSA reduces {primavera,
mamanthal, salsa, resorte} to one word giving 2 bits saving on Hutter.
- Ian Parker
On 29 June 2010 07:32, rob levy r.p.l...@gmail.com wrote:
Sorry, the link I included was invalid, this is what I meant:
http://www.geog.ucsb.edu/~raubal/Publications/RefConferences/ICSC_2009_AdamsRaubal_Camera-FINAL.pdfhttp://www.geog.ucsb.edu/%7Eraubal/Publications/RefConferences/ICSC_2009_AdamsRaubal_Camera-FINAL.pdf
On Tue, Jun 29, 2010 at 2:28 AM, rob levy r.p.l...@gmail.com wrote:
On Mon, Jun 28, 2010 at 5:23 PM, Steve Richfield
steve.richfi...@gmail.com wrote:
Rob,
I just LOVE opaque postings, because they identify people who see things
differently than I do. I'm not sure what you are saying here, so I'll make
some random responses to exhibit my ignorance and elicit more
explanation.
I think based on what you wrote, you understood (mostly) what I was
trying to get across. So I'm glad it was at least quasi-intelligible. :)
It sounds like this is a finer measure than the dimensionality that I
was referencing. However, I don't see how to reduce anything as quantized
as
dimensionality into finer measures. Can you say some more about this?
I was just referencing Gardenfors' research program of conceptual
spaces (I was intentionally vague about committing to this fully though
because I don't necessarily think this is the whole answer). Page 2 of this
article summarizes it pretty succinctly: http://http://goog_1627994790
www.geog.ucsb.edu/.../ICSC_2009_AdamsRaubal_Camera-FINAL.pdf
However, different people's brains, even the brains of identical twins,
have DIFFERENT mappings. This would seem to mandate experience-formed
topology.
Yes definitely.
Since these conceptual spaces that structure sensorimotor
expectation/prediction (including in higher order embodied exploration of
concepts I think) are multidimensional spaces, it seems likely that some
kind of neural computation over these spaces must occur,
I agree.
though I wonder what it actually would be in terms of neurons, (and if
that matters).
I don't see any route to the answer except via neurons.
I agree this is true of natural intelligence, though maybe in modeling,
the neural level can be shortcut to the topo map level without recourse to
neural computation (use some more straightforward computation like matrix
algebra instead).
Rob
*agi* | Archives https://www.listbox.com/member/archive/303/=now
https://www.listbox.com/member/archive/rss/303/ |
Modifyhttps://www.listbox.com/member/?;Your Subscription
http://www.listbox.com
*agi* | Archives https://www.listbox.com/member/archive/303/=now
https://www.listbox.com/member/archive/rss/303/ |
Modifyhttps://www.listbox.com/member/?;Your Subscription
http://www.listbox.com
---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c
Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
There is very little. Someone do research. Here is a paper on language
fitness.
http://kybele.psych.cornell.edu/~edelman/elcfinal.pdf
http://kybele.psych.cornell.edu/~edelman/elcfinal.pdfLSA is *not* discussed
nor is any fitness concept with the language itself. Similar sounding (or
written) words must be capable of disambiguation using LSA, otherwise the
language would be unfit. Let us have a *gedanken* language where spring
the example I have taken with my Spanish cannot be disambiguated. Suppose *
spring* meant *step forward, *as well as its other meanings. If I am
learning to dance I do not think about *primavera, resorte *or*
mamanthal* but
I do think about *salsa*. If I did not know whether I was to jump or put
my leg forward it would be extremely confusing. To my knowledge fitness in
this context has not been discussed.
In fact perhaps the only work that is relevant is my own which I posted here
some time ago. The reduction in entropy (compression) obtained with LSA was
disappointing. The different meanings (different words in Spanish other
languages) are compressed more readily. Both Spanish and English have a
degree of fitness which (just possibly) is definable in LSA terms.
- Ian Parker
On 7 July 2010 17:12, Gabriel Recchia grecc...@gmail.com wrote:
In short, instead of a pot of neurons, we might instead have a pot of
dozens of types of
neurons that each have their own complex rules regarding what other types
of neurons they
can connect to, and how they process information...
...there is plenty of evidence (from the slowness of evolution, the large
number (~200)
of neuron types, etc.), that it is many-layered and quite complex...
The disconnect between the low-level neural hardware and the implementation
of algorithms that build conceptual spaces via dimensionality
reduction--which generally ignore facts such as the existence of different
types of neurons, the apparently hierarchical organization of neocortex,
etc.--seems significant. Have there been attempts to develop computational
models capable of LSA-style feats (e.g., constructing a vector space in
which words with similar meanings tend to be relatively close to each other)
that take into account basic facts about how neurons actually operate
(ideally in a more sophisticated way than the nodes of early connectionist
networks which, as we now know, are not particularly neuron-like at all)? If
so, I would love to know about them.
On Tue, Jun 29, 2010 at 3:02 PM, Ian Parker ianpark...@gmail.com wrote:
The paper seems very similar in principle to LSA. What you need for a
concept vector (or position) is the application of LSA followed by K-Means
which will give you your concept clusters.
I would not knock Hutter too much. After all LSA reduces {primavera,
mamanthal, salsa, resorte} to one word giving 2 bits saving on Hutter.
- Ian Parker
On 29 June 2010 07:32, rob levy r.p.l...@gmail.com wrote:
Sorry, the link I included was invalid, this is what I meant:
http://www.geog.ucsb.edu/~raubal/Publications/RefConferences/ICSC_2009_AdamsRaubal_Camera-FINAL.pdfhttp://www.geog.ucsb.edu/%7Eraubal/Publications/RefConferences/ICSC_2009_AdamsRaubal_Camera-FINAL.pdf
On Tue, Jun 29, 2010 at 2:28 AM, rob levy r.p.l...@gmail.com wrote:
On Mon, Jun 28, 2010 at 5:23 PM, Steve Richfield
steve.richfi...@gmail.com wrote:
Rob,
I just LOVE opaque postings, because they identify people who see
things differently than I do. I'm not sure what you are saying here, so
I'll
make some random responses to exhibit my ignorance and elicit more
explanation.
I think based on what you wrote, you understood (mostly) what I was
trying to get across. So I'm glad it was at least quasi-intelligible. :)
It sounds like this is a finer measure than the dimensionality that
I was referencing. However, I don't see how to reduce anything as
quantized
as dimensionality into finer measures. Can you say some more about this?
I was just referencing Gardenfors' research program of conceptual
spaces (I was intentionally vague about committing to this fully though
because I don't necessarily think this is the whole answer). Page 2 of
this
article summarizes it pretty succinctly: http://http://goog_1627994790
www.geog.ucsb.edu/.../ICSC_2009_AdamsRaubal_Camera-FINAL.pdf
However, different people's brains, even the brains of identical twins,
have DIFFERENT mappings. This would seem to mandate experience-formed
topology.
Yes definitely.
Since these conceptual spaces that structure sensorimotor
expectation/prediction (including in higher order embodied exploration of
concepts I think) are multidimensional spaces, it seems likely that some
kind of neural computation over these spaces must occur,
I agree.
though I wonder what it actually would be in terms of neurons, (and if
that matters).
I don't see any route to the answer except via neurons.
I agree this is true of natural
Re: [agi] Hutter - A fundamental misdirection?
Gorrell and Webb describe a neural implementation of LSA that seems more
biologically plausible than the usual matrix factoring implementation.
http://www.dcs.shef.ac.uk/~genevieve/gorrell_webb.pdf
In the usual implementation, a word-word matrix A is factored to A = USV where
S
is diagonal (containing eigenvalues), and then the smaller elements of S are
discarded. In the Gorrell model, U and V are the weights of a 3 layer neural
network mapping words to words, and the nonzero elements of S represent the
semantic space in the middle layer. As the network is trained, neurons are
added
to S. Thus, the network is trained online in a single pass, unlike factoring,
which is offline.
-- Matt Mahoney, matmaho...@yahoo.com
From: Gabriel Recchia grecc...@gmail.com
To: agi agi@v2.listbox.com
Sent: Wed, July 7, 2010 12:12:00 PM
Subject: Re: [agi] Hutter - A fundamental misdirection?
In short, instead of a pot of neurons, we might instead have a pot of
dozens
of types of
neurons that each have their own complex rules regarding what other types of
neurons they
can connect to, and how they process information...
...there is plenty of evidence (from the slowness of evolution, the large
number (~200)
of neuron types, etc.), that it is many-layered and quite complex...
The disconnect between the low-level neural hardware and the implementation of
algorithms that build conceptual spaces via dimensionality reduction--which
generally ignore facts such as the existence of different types of neurons, the
apparently hierarchical organization of neocortex, etc.--seems significant.
Have
there been attempts to develop computational models capable of LSA-style feats
(e.g., constructing a vector space in which words with similar meanings tend to
be relatively close to each other) that take into account basic facts about how
neurons actually operate (ideally in a more sophisticated way than the nodes of
early connectionist networks which, as we now know, are not particularly
neuron-like at all)? If so, I would love to know about them.
On Tue, Jun 29, 2010 at 3:02 PM, Ian Parker ianpark...@gmail.com wrote:
The paper seems very similar in principle to LSA. What you need for a concept
vector (or position) is the application of LSA followed by K-Means which will
give you your concept clusters.
I would not knock Hutter too much. After all LSA reduces {primavera,
mamanthal,
salsa, resorte} to one word giving 2 bits saving on Hutter.
- Ian Parker
On 29 June 2010 07:32, rob levy r.p.l...@gmail.com wrote:
Sorry, the link I included was invalid, this is what I meant:
http://www.geog.ucsb.edu/~raubal/Publications/RefConferences/ICSC_2009_AdamsRaubal_Camera-FINAL.pdf
On Tue, Jun 29, 2010 at 2:28 AM, rob levy r.p.l...@gmail.com wrote:
On Mon, Jun 28, 2010 at 5:23 PM, Steve Richfield steve.richfi...@gmail.com
wrote:
Rob,
I just LOVE opaque postings, because they identify people who see things
differently than I do. I'm not sure what you are saying here, so I'll make
some
random responses to exhibit my ignorance and elicit more explanation.
I think based on what you wrote, you understood (mostly) what I was trying
to
get across. So I'm glad it was at least quasi-intelligible. :)
It sounds like this is a finer measure than the dimensionality that I was
referencing. However, I don't see how to reduce anything as quantized as
dimensionality into finer measures. Can you say some more about this?
I was just referencing Gardenfors' research program of conceptual spaces
(I
was intentionally vague about committing to this fully though because I
don't
necessarily think this is the whole answer). Page 2 of this article
summarizes
it pretty succinctly:
http://www.geog.ucsb.edu/.../ICSC_2009_AdamsRaubal_Camera-FINAL.pdf
However, different people's brains, even the brains of identical twins, have
DIFFERENT mappings. This would seem to mandate experience-formed topology.
Yes definitely.
Since these conceptual spaces that structure sensorimotor
expectation/prediction
(including in higher order embodied exploration of concepts I think) are
multidimensional spaces, it seems likely that some kind of neural
computation
over these spaces must occur,
I agree.
though I wonder what it actually would be in terms of neurons, (and if that
matters).
I don't see any route to the answer except via neurons.
I agree this is true of natural intelligence, though maybe in modeling, the
neural level can be shortcut to the topo map level without recourse to
neural
computation (use some more straightforward computation like matrix algebra
instead).
Rob
agi | Archives | Modify Your Subscription
agi | Archives | Modify Your Subscription
agi | Archives | Modify Your Subscription
---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https
Re: [agi] Hutter - A fundamental misdirection?
On Mon, Jun 28, 2010 at 5:23 PM, Steve Richfield steve.richfi...@gmail.comwrote: Rob, I just LOVE opaque postings, because they identify people who see things differently than I do. I'm not sure what you are saying here, so I'll make some random responses to exhibit my ignorance and elicit more explanation. I think based on what you wrote, you understood (mostly) what I was trying to get across. So I'm glad it was at least quasi-intelligible. :) It sounds like this is a finer measure than the dimensionality that I was referencing. However, I don't see how to reduce anything as quantized as dimensionality into finer measures. Can you say some more about this? I was just referencing Gardenfors' research program of conceptual spaces (I was intentionally vague about committing to this fully though because I don't necessarily think this is the whole answer). Page 2 of this article summarizes it pretty succinctly: http:// goog_1627994790 www.geog.ucsb.edu/.../ICSC_2009_AdamsRaubal_Camera-FINAL.pdf However, different people's brains, even the brains of identical twins, have DIFFERENT mappings. This would seem to mandate experience-formed topology. Yes definitely. Since these conceptual spaces that structure sensorimotor expectation/prediction (including in higher order embodied exploration of concepts I think) are multidimensional spaces, it seems likely that some kind of neural computation over these spaces must occur, I agree. though I wonder what it actually would be in terms of neurons, (and if that matters). I don't see any route to the answer except via neurons. I agree this is true of natural intelligence, though maybe in modeling, the neural level can be shortcut to the topo map level without recourse to neural computation (use some more straightforward computation like matrix algebra instead). Rob --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
Sorry, the link I included was invalid, this is what I meant: http://www.geog.ucsb.edu/~raubal/Publications/RefConferences/ICSC_2009_AdamsRaubal_Camera-FINAL.pdf On Tue, Jun 29, 2010 at 2:28 AM, rob levy r.p.l...@gmail.com wrote: On Mon, Jun 28, 2010 at 5:23 PM, Steve Richfield steve.richfi...@gmail.com wrote: Rob, I just LOVE opaque postings, because they identify people who see things differently than I do. I'm not sure what you are saying here, so I'll make some random responses to exhibit my ignorance and elicit more explanation. I think based on what you wrote, you understood (mostly) what I was trying to get across. So I'm glad it was at least quasi-intelligible. :) It sounds like this is a finer measure than the dimensionality that I was referencing. However, I don't see how to reduce anything as quantized as dimensionality into finer measures. Can you say some more about this? I was just referencing Gardenfors' research program of conceptual spaces (I was intentionally vague about committing to this fully though because I don't necessarily think this is the whole answer). Page 2 of this article summarizes it pretty succinctly: http:// http://goog_1627994790 www.geog.ucsb.edu/.../ICSC_2009_AdamsRaubal_Camera-FINAL.pdf However, different people's brains, even the brains of identical twins, have DIFFERENT mappings. This would seem to mandate experience-formed topology. Yes definitely. Since these conceptual spaces that structure sensorimotor expectation/prediction (including in higher order embodied exploration of concepts I think) are multidimensional spaces, it seems likely that some kind of neural computation over these spaces must occur, I agree. though I wonder what it actually would be in terms of neurons, (and if that matters). I don't see any route to the answer except via neurons. I agree this is true of natural intelligence, though maybe in modeling, the neural level can be shortcut to the topo map level without recourse to neural computation (use some more straightforward computation like matrix algebra instead). Rob --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
The paper seems very similar in principle to LSA. What you need for a
concept vector (or position) is the application of LSA followed by K-Means
which will give you your concept clusters.
I would not knock Hutter too much. After all LSA reduces {primavera,
mamanthal, salsa, resorte} to one word giving 2 bits saving on Hutter.
- Ian Parker
On 29 June 2010 07:32, rob levy r.p.l...@gmail.com wrote:
Sorry, the link I included was invalid, this is what I meant:
http://www.geog.ucsb.edu/~raubal/Publications/RefConferences/ICSC_2009_AdamsRaubal_Camera-FINAL.pdf
On Tue, Jun 29, 2010 at 2:28 AM, rob levy r.p.l...@gmail.com wrote:
On Mon, Jun 28, 2010 at 5:23 PM, Steve Richfield
steve.richfi...@gmail.com wrote:
Rob,
I just LOVE opaque postings, because they identify people who see things
differently than I do. I'm not sure what you are saying here, so I'll make
some random responses to exhibit my ignorance and elicit more explanation.
I think based on what you wrote, you understood (mostly) what I was trying
to get across. So I'm glad it was at least quasi-intelligible. :)
It sounds like this is a finer measure than the dimensionality that I
was referencing. However, I don't see how to reduce anything as quantized as
dimensionality into finer measures. Can you say some more about this?
I was just referencing Gardenfors' research program of conceptual spaces
(I was intentionally vague about committing to this fully though because I
don't necessarily think this is the whole answer). Page 2 of this article
summarizes it pretty succinctly: http:// http://goog_1627994790
www.geog.ucsb.edu/.../ICSC_2009_AdamsRaubal_Camera-FINAL.pdf
However, different people's brains, even the brains of identical twins,
have DIFFERENT mappings. This would seem to mandate experience-formed
topology.
Yes definitely.
Since these conceptual spaces that structure sensorimotor
expectation/prediction (including in higher order embodied exploration of
concepts I think) are multidimensional spaces, it seems likely that some
kind of neural computation over these spaces must occur,
I agree.
though I wonder what it actually would be in terms of neurons, (and if
that matters).
I don't see any route to the answer except via neurons.
I agree this is true of natural intelligence, though maybe in modeling,
the neural level can be shortcut to the topo map level without recourse to
neural computation (use some more straightforward computation like matrix
algebra instead).
Rob
*agi* | Archives https://www.listbox.com/member/archive/303/=now
https://www.listbox.com/member/archive/rss/303/ |
Modifyhttps://www.listbox.com/member/?;Your Subscription
http://www.listbox.com
---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c
Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
In order to have perceptual/conceptual similarity, it might make sense that there is distance metric over conceptual spaces mapping (ala Gardenfors or something like this theory) underlying how the experience of reasoning through is carried out. This has the advantage of being motivated by neuroscience findings (which are seldom convincing, but in this case it is basic solid neuroscience research) that there are topographic maps in the brain. Since these conceptual spaces that structure sensorimotor expectation/prediction (including in higher order embodied exploration of concepts I think) are multidimensional spaces, it seems likely that some kind of neural computation over these spaces must occur, though I wonder what it actually would be in terms of neurons, (and if that matters). But that is different from what would be considered quantitative reasoning, because from the phenomenological perspective the person is training sensorimotor expectations by perceiving and doing. And creative conceptual shifts (or recognition of novel perceptual categories) can also be explained by this feedback between trained topographic maps and embodied interaction with environment (experienced at the ecological level as sensorimotor expectations (driven by neural maps). Sensorimotor expectation is the basis of dynamics of perception and coceptualization). On Sun, Jun 27, 2010 at 7:24 PM, Ben Goertzel b...@goertzel.org wrote: On Sun, Jun 27, 2010 at 7:09 PM, Steve Richfield steve.richfi...@gmail.com wrote: Ben, On Sun, Jun 27, 2010 at 3:47 PM, Ben Goertzel b...@goertzel.org wrote: know what dimensional analysis is, but it would be great if you could give an example of how it's useful for everyday commonsense reasoning such as, say, a service robot might need to do to figure out how to clean a house... How much detergent will it need to clean the floors? Hmmm, we need to know ounces. We have the length and width of the floor, and the bottle says to use 1 oz/M^2. How could we manipulate two M-dimensioned quantities and 1 oz/M^2 dimensioned quantity to get oz? The only way would seem to be to multiply all three numbers together to get ounces. This WITHOUT understanding things like surface area, utilization, etc. I think that the El Salvadorean maids who come to clean my house occasionally, solve this problem without any dimensional analysis or any quantitative reasoning at all... Probably they solve it based on nearest-neighbor matching against past experiences cleaning other dirty floors with water in similarly sized and shaped buckets... -- ben g *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
Rob, I just LOVE opaque postings, because they identify people who see things differently than I do. I'm not sure what you are saying here, so I'll make some random responses to exhibit my ignorance and elicit more explanation. On Mon, Jun 28, 2010 at 9:53 AM, rob levy r.p.l...@gmail.com wrote: In order to have perceptual/conceptual similarity, it might make sense that there is distance metric over conceptual spaces mapping It sounds like this is a finer measure than the dimensionality that I was referencing. However, I don't see how to reduce anything as quantized as dimensionality into finer measures. Can you say some more about this? (ala Gardenfors or something like this theory) underlying how the experience of reasoning through is carried out. This has the advantage of being motivated by neuroscience findings (which are seldom convincing, but in this case it is basic solid neuroscience research) that there are topographic maps in the brain. However, different people's brains, even the brains of identical twins, have DIFFERENT mappings. This would seem to mandate experience-formed topology. Since these conceptual spaces that structure sensorimotor expectation/prediction (including in higher order embodied exploration of concepts I think) are multidimensional spaces, it seems likely that some kind of neural computation over these spaces must occur, I agree. though I wonder what it actually would be in terms of neurons, (and if that matters). I don't see any route to the answer except via neurons. But that is different from what would be considered quantitative reasoning, because from the phenomenological perspective the person is training sensorimotor expectations by perceiving and doing. And creative conceptual shifts (or recognition of novel perceptual categories) can also be explained by this feedback between trained topographic maps and embodied interaction with environment (experienced at the ecological level as sensorimotor expectations (driven by neural maps). Sensorimotor expectation is the basis of dynamics of perception and coceptualization). All of which is computation of various sorts, the basics of which need to be understood. Steve = On Sun, Jun 27, 2010 at 7:24 PM, Ben Goertzel b...@goertzel.org wrote: On Sun, Jun 27, 2010 at 7:09 PM, Steve Richfield steve.richfi...@gmail.com wrote: Ben, On Sun, Jun 27, 2010 at 3:47 PM, Ben Goertzel b...@goertzel.org wrote: know what dimensional analysis is, but it would be great if you could give an example of how it's useful for everyday commonsense reasoning such as, say, a service robot might need to do to figure out how to clean a house... How much detergent will it need to clean the floors? Hmmm, we need to know ounces. We have the length and width of the floor, and the bottle says to use 1 oz/M^2. How could we manipulate two M-dimensioned quantities and 1 oz/M^2 dimensioned quantity to get oz? The only way would seem to be to multiply all three numbers together to get ounces. This WITHOUT understanding things like surface area, utilization, etc. I think that the El Salvadorean maids who come to clean my house occasionally, solve this problem without any dimensional analysis or any quantitative reasoning at all... Probably they solve it based on nearest-neighbor matching against past experiences cleaning other dirty floors with water in similarly sized and shaped buckets... -- ben g *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com *agi* | Archives https://www.listbox.com/member/archive/303/=now https://www.listbox.com/member/archive/rss/303/ | Modifyhttps://www.listbox.com/member/?;Your Subscription http://www.listbox.com --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Hutter - A fundamental misdirection?
Hi Steve, A few comments... 1) Nobody is trying to implement Hutter's AIXI design, it's a mathematical design intended as a proof of principle 2) Within Hutter's framework, one calculates the shortest program that explains the data, where shortest is measured on Turing machine M. Given a sufficient number of observations, the choice of M doesn't matter and AIXI will eventually learn any computable reward pattern. However, choosing the right M can greatly accelerate learning. In the case of a physical AGI system, choosing M to incorporate the correct laws of physics would obviously accelerate learning considerably. 3) Many AGI designs try to incorporate prior understanding of the structure properties of the physical world, in various ways. I have a whole chapter on this in my forthcoming book on OpenCog E.g. OpenCog's design includes a physics-engine, which is used directly and to aid with inferential extrapolations... So I agree with most of your points, but I don't find them original except in phrasing ;) ... ben On Sun, Jun 27, 2010 at 2:30 PM, Steve Richfield steve.richfi...@gmail.comwrote: Ben, et al, *I think I may finally grok the fundamental misdirection that current AGI thinking has taken! *This is a bit subtle, and hence subject to misunderstanding. Therefore I will first attempt to explain what I see, WITHOUT so much trying to convince you (or anyone) that it is necessarily correct. Once I convey my vision, then let the chips fall where they may. On Sun, Jun 27, 2010 at 6:35 AM, Ben Goertzel b...@goertzel.org wrote: Hutter's AIXI for instance works [very roughly speaking] by choosing the most compact program that, based on historical data, would have yielded maximum reward ... and there it is! What did I see? Example applicable to the lengthy following discussion: 1 - 2 2 - 2 3 - 2 4 - 2 5 - ? What is ?. Now, I'll tell you that the left column represents the distance along a 4.5 unit long table, and the right column represents the distance above the floor that you will be as your walk the length of the table. Knowing this, without ANY supporting physical experience, I would guess ? to be zero, or maybe a little more if I were to step off of the table and land onto something lower, like the shoes that I left there. In an imaginary world where a GI boots up with a complete understanding of physics, etc., we wouldn't prefer the simplest program at all, but rather the simplest representation of the real world that is not physics/math *in *consistent with our observations. All observations would be presumed to be consistent with the response curves of our sensors, showing a world in which Newton's laws prevail, etc. Armed with these presumptions, our physics-complete AGI would look for the simplest set of *UN*observed phenomena that explained the observed phenomena. This theory of a physics-complete AGI seems undeniable, but of course, we are NOT born physics-complete - or are we?! This all comes down to the limits of representational math. At great risk of hand-waving on a keyboard, I'll try to explain by pseudo-translating the concepts into NN/AGI terms. We all know about layering and columns in neural systems, and understand Bayesian math. However, let's dig a little deeper into exactly what is being represented by the outputs (or terms for died-in-the-wool AGIers). All physical quantities are well known to have value, significance, and dimensionality. Neurons/Terms (N/T) could easily be protein-tagged as to the dimensionality that their functionality is capable of producing, so that only compatible N/Ts could connect to them. However, let's dig a little deeper into dimensionality Physicists think we live in an MKS (Meters, Kilograms, Seconds) world, and that all dimensionality can be reduced to MKS. For physics purposes they may be right (see challenge below), but maybe for information processing purposes, they are missing some important things. *Challenge to MKS:* Note that some physicists and most astronomers utilize *dimensional analysis* where they experimentally play with the dimensions of observations to inductively find manipulations that would yield the dimensions of unobservable quantities, e.g. the mass of a star, and then run the numbers through the same manipulation to see if the results at least have the right exponent. However, many/most such manipulations produce nonsense, so they simply use this technique to jump from observations to a list of prospective results with wildly different exponents, and discard the results with the ridiculous exponents to find the correct result. The frequent failures of this process indirectly demonstrates that there is more to dimensionality (and hence physics) than just MKS. Let's accept that, and presume that neurons must have already dealt with whatever is missing from current thought. Consider, there is some (hopefully finite) set of reasonable
Re: [agi] Hutter - A fundamental misdirection?
Ben, What I saw as my central thesis is that propagating carefully conceived dimensionality information along with classical information could greatly improve the cognitive process, by FORCING reasonable physics WITHOUT having to understand (by present concepts of what understanding means) physics. Hutter was just a foil to explain my thought. Note again my comments regarding how physicists and astronomers understand some processes though dimensional analysis that involves NONE of the sorts of understanding that you might think necessary, yet can predictably come up with the right answers. Are you up on the basics of dimensional analysis? The reality is that it is quite imperfect, but is often able to yield a short list of answers, with the correct one being somewhere in the list. Usually, the wrong answers are wildly wrong (they are probably computing something, but NOT what you might be interested in), and are hence easily eliminated. I suspect that neurons might be doing much the same, as could formulaic implementations like (most) present AGI efforts. This might explain natural architecture and guide human architectural efforts. In short, instead of a pot of neurons, we might instead have a pot of dozens of types of neurons that each have their own complex rules regarding what other types of neurons they can connect to, and how they process information. Architecture might involve deciding how many of each type to provide, and what types to put adjacent to what other types, rather than the more detailed concept now usually thought to exist. Thanks for helping me wring my thought out here. Steve = On Sun, Jun 27, 2010 at 2:49 PM, Ben Goertzel b...@goertzel.org wrote: Hi Steve, A few comments... 1) Nobody is trying to implement Hutter's AIXI design, it's a mathematical design intended as a proof of principle 2) Within Hutter's framework, one calculates the shortest program that explains the data, where shortest is measured on Turing machine M. Given a sufficient number of observations, the choice of M doesn't matter and AIXI will eventually learn any computable reward pattern. However, choosing the right M can greatly accelerate learning. In the case of a physical AGI system, choosing M to incorporate the correct laws of physics would obviously accelerate learning considerably. 3) Many AGI designs try to incorporate prior understanding of the structure properties of the physical world, in various ways. I have a whole chapter on this in my forthcoming book on OpenCog E.g. OpenCog's design includes a physics-engine, which is used directly and to aid with inferential extrapolations... So I agree with most of your points, but I don't find them original except in phrasing ;) ... ben On Sun, Jun 27, 2010 at 2:30 PM, Steve Richfield steve.richfi...@gmail.com wrote: Ben, et al, *I think I may finally grok the fundamental misdirection that current AGI thinking has taken! *This is a bit subtle, and hence subject to misunderstanding. Therefore I will first attempt to explain what I see, WITHOUT so much trying to convince you (or anyone) that it is necessarily correct. Once I convey my vision, then let the chips fall where they may. On Sun, Jun 27, 2010 at 6:35 AM, Ben Goertzel b...@goertzel.org wrote: Hutter's AIXI for instance works [very roughly speaking] by choosing the most compact program that, based on historical data, would have yielded maximum reward ... and there it is! What did I see? Example applicable to the lengthy following discussion: 1 - 2 2 - 2 3 - 2 4 - 2 5 - ? What is ?. Now, I'll tell you that the left column represents the distance along a 4.5 unit long table, and the right column represents the distance above the floor that you will be as your walk the length of the table. Knowing this, without ANY supporting physical experience, I would guess ? to be zero, or maybe a little more if I were to step off of the table and land onto something lower, like the shoes that I left there. In an imaginary world where a GI boots up with a complete understanding of physics, etc., we wouldn't prefer the simplest program at all, but rather the simplest representation of the real world that is not physics/math * in*consistent with our observations. All observations would be presumed to be consistent with the response curves of our sensors, showing a world in which Newton's laws prevail, etc. Armed with these presumptions, our physics-complete AGI would look for the simplest set of *UN*observed phenomena that explained the observed phenomena. This theory of a physics-complete AGI seems undeniable, but of course, we are NOT born physics-complete - or are we?! This all comes down to the limits of representational math. At great risk of hand-waving on a keyboard, I'll try to explain by pseudo-translating the concepts into NN/AGI terms. We all know about layering and columns in neural systems, and
Re: [agi] Hutter - A fundamental misdirection?
Steve, I know what dimensional analysis is, but it would be great if you could give an example of how it's useful for everyday commonsense reasoning such as, say, a service robot might need to do to figure out how to clean a house... thx ben On Sun, Jun 27, 2010 at 6:43 PM, Steve Richfield steve.richfi...@gmail.comwrote: Ben, What I saw as my central thesis is that propagating carefully conceived dimensionality information along with classical information could greatly improve the cognitive process, by FORCING reasonable physics WITHOUT having to understand (by present concepts of what understanding means) physics. Hutter was just a foil to explain my thought. Note again my comments regarding how physicists and astronomers understand some processes though dimensional analysis that involves NONE of the sorts of understanding that you might think necessary, yet can predictably come up with the right answers. Are you up on the basics of dimensional analysis? The reality is that it is quite imperfect, but is often able to yield a short list of answers, with the correct one being somewhere in the list. Usually, the wrong answers are wildly wrong (they are probably computing something, but NOT what you might be interested in), and are hence easily eliminated. I suspect that neurons might be doing much the same, as could formulaic implementations like (most) present AGI efforts. This might explain natural architecture and guide human architectural efforts. In short, instead of a pot of neurons, we might instead have a pot of dozens of types of neurons that each have their own complex rules regarding what other types of neurons they can connect to, and how they process information. Architecture might involve deciding how many of each type to provide, and what types to put adjacent to what other types, rather than the more detailed concept now usually thought to exist. Thanks for helping me wring my thought out here. Steve = On Sun, Jun 27, 2010 at 2:49 PM, Ben Goertzel b...@goertzel.org wrote: Hi Steve, A few comments... 1) Nobody is trying to implement Hutter's AIXI design, it's a mathematical design intended as a proof of principle 2) Within Hutter's framework, one calculates the shortest program that explains the data, where shortest is measured on Turing machine M. Given a sufficient number of observations, the choice of M doesn't matter and AIXI will eventually learn any computable reward pattern. However, choosing the right M can greatly accelerate learning. In the case of a physical AGI system, choosing M to incorporate the correct laws of physics would obviously accelerate learning considerably. 3) Many AGI designs try to incorporate prior understanding of the structure properties of the physical world, in various ways. I have a whole chapter on this in my forthcoming book on OpenCog E.g. OpenCog's design includes a physics-engine, which is used directly and to aid with inferential extrapolations... So I agree with most of your points, but I don't find them original except in phrasing ;) ... ben On Sun, Jun 27, 2010 at 2:30 PM, Steve Richfield steve.richfi...@gmail.com wrote: Ben, et al, *I think I may finally grok the fundamental misdirection that current AGI thinking has taken! *This is a bit subtle, and hence subject to misunderstanding. Therefore I will first attempt to explain what I see, WITHOUT so much trying to convince you (or anyone) that it is necessarily correct. Once I convey my vision, then let the chips fall where they may. On Sun, Jun 27, 2010 at 6:35 AM, Ben Goertzel b...@goertzel.org wrote: Hutter's AIXI for instance works [very roughly speaking] by choosing the most compact program that, based on historical data, would have yielded maximum reward ... and there it is! What did I see? Example applicable to the lengthy following discussion: 1 - 2 2 - 2 3 - 2 4 - 2 5 - ? What is ?. Now, I'll tell you that the left column represents the distance along a 4.5 unit long table, and the right column represents the distance above the floor that you will be as your walk the length of the table. Knowing this, without ANY supporting physical experience, I would guess ? to be zero, or maybe a little more if I were to step off of the table and land onto something lower, like the shoes that I left there. In an imaginary world where a GI boots up with a complete understanding of physics, etc., we wouldn't prefer the simplest program at all, but rather the simplest representation of the real world that is not physics/math *in*consistent with our observations. All observations would be presumed to be consistent with the response curves of our sensors, showing a world in which Newton's laws prevail, etc. Armed with these presumptions, our physics-complete AGI would look for the simplest set of *UN*observed phenomena that explained the observed phenomena. This theory of a
Re: [agi] Hutter - A fundamental misdirection?
Ben, On Sun, Jun 27, 2010 at 3:47 PM, Ben Goertzel b...@goertzel.org wrote: know what dimensional analysis is, but it would be great if you could give an example of how it's useful for everyday commonsense reasoning such as, say, a service robot might need to do to figure out how to clean a house... How much detergent will it need to clean the floors? Hmmm, we need to know ounces. We have the length and width of the floor, and the bottle says to use 1 oz/M^2. How could we manipulate two M-dimensioned quantities and 1 oz/M^2 dimensioned quantity to get oz? The only way would seem to be to multiply all three numbers together to get ounces. This WITHOUT understanding things like surface area, utilization, etc. Of course, throw in a few other available measures and it become REALLY easy to come up with several wrong answers. This method does NOT avoid wrong answers, it only provides a mechanism to have the right answer among them. While this may be a challenge for dispensing detergent (especially if you include the distance from the earth to the sun as one of your available measures), it is little problem for learning. I was more concerned with learning than with solving. I believe that dimensional analysis could help learning a LOT, by maximally constraining what is used as a basis for learning, without throwing the baby out with the bathwater, i.e. applying so much constraint that a good solution can't climb out of the process. Steve On Sun, Jun 27, 2010 at 6:43 PM, Steve Richfield steve.richfi...@gmail.comwrote: Ben, What I saw as my central thesis is that propagating carefully conceived dimensionality information along with classical information could greatly improve the cognitive process, by FORCING reasonable physics WITHOUT having to understand (by present concepts of what understanding means) physics. Hutter was just a foil to explain my thought. Note again my comments regarding how physicists and astronomers understand some processes though dimensional analysis that involves NONE of the sorts of understanding that you might think necessary, yet can predictably come up with the right answers. Are you up on the basics of dimensional analysis? The reality is that it is quite imperfect, but is often able to yield a short list of answers, with the correct one being somewhere in the list. Usually, the wrong answers are wildly wrong (they are probably computing something, but NOT what you might be interested in), and are hence easily eliminated. I suspect that neurons might be doing much the same, as could formulaic implementations like (most) present AGI efforts. This might explain natural architecture and guide human architectural efforts. In short, instead of a pot of neurons, we might instead have a pot of dozens of types of neurons that each have their own complex rules regarding what other types of neurons they can connect to, and how they process information. Architecture might involve deciding how many of each type to provide, and what types to put adjacent to what other types, rather than the more detailed concept now usually thought to exist. Thanks for helping me wring my thought out here. Steve = On Sun, Jun 27, 2010 at 2:49 PM, Ben Goertzel b...@goertzel.org wrote: Hi Steve, A few comments... 1) Nobody is trying to implement Hutter's AIXI design, it's a mathematical design intended as a proof of principle 2) Within Hutter's framework, one calculates the shortest program that explains the data, where shortest is measured on Turing machine M. Given a sufficient number of observations, the choice of M doesn't matter and AIXI will eventually learn any computable reward pattern. However, choosing the right M can greatly accelerate learning. In the case of a physical AGI system, choosing M to incorporate the correct laws of physics would obviously accelerate learning considerably. 3) Many AGI designs try to incorporate prior understanding of the structure properties of the physical world, in various ways. I have a whole chapter on this in my forthcoming book on OpenCog E.g. OpenCog's design includes a physics-engine, which is used directly and to aid with inferential extrapolations... So I agree with most of your points, but I don't find them original except in phrasing ;) ... ben On Sun, Jun 27, 2010 at 2:30 PM, Steve Richfield steve.richfi...@gmail.com wrote: Ben, et al, *I think I may finally grok the fundamental misdirection that current AGI thinking has taken! *This is a bit subtle, and hence subject to misunderstanding. Therefore I will first attempt to explain what I see, WITHOUT so much trying to convince you (or anyone) that it is necessarily correct. Once I convey my vision, then let the chips fall where they may. On Sun, Jun 27, 2010 at 6:35 AM, Ben Goertzel b...@goertzel.org wrote: Hutter's AIXI for instance works [very roughly speaking] by choosing the most
Re: [agi] Hutter - A fundamental misdirection?
On Sun, Jun 27, 2010 at 7:09 PM, Steve Richfield steve.richfi...@gmail.comwrote: Ben, On Sun, Jun 27, 2010 at 3:47 PM, Ben Goertzel b...@goertzel.org wrote: know what dimensional analysis is, but it would be great if you could give an example of how it's useful for everyday commonsense reasoning such as, say, a service robot might need to do to figure out how to clean a house... How much detergent will it need to clean the floors? Hmmm, we need to know ounces. We have the length and width of the floor, and the bottle says to use 1 oz/M^2. How could we manipulate two M-dimensioned quantities and 1 oz/M^2 dimensioned quantity to get oz? The only way would seem to be to multiply all three numbers together to get ounces. This WITHOUT understanding things like surface area, utilization, etc. I think that the El Salvadorean maids who come to clean my house occasionally, solve this problem without any dimensional analysis or any quantitative reasoning at all... Probably they solve it based on nearest-neighbor matching against past experiences cleaning other dirty floors with water in similarly sized and shaped buckets... -- ben g --- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
