Who's on Friston? Me and my Markov Blanket

classic Classic list List threaded Threaded
7 messages Options
Reply | Threaded
Open this post in threaded view
|

Who's on Friston? Me and my Markov Blanket

Stephen Guerin-5
Eric Smith and Frank,

Eric,  I'd be curious what you think of Karl Friston's talk. 
 https://www.santafe.edu/events/me-and-my-markov-blanket

Perhaps better that he moved away from calling his work the "Free Energy Principle" and now using the term "Bayesian Mechanics"

Frank, I do find the Markov Blanket/Boundary interesting noting that it originated with Judea Pearl. Did you, Peter and Clark work with Markov Boundaries in your Causal Inference? 

-S
_______________________________________________________________________
[hidden email]
CEO, Simtable  http://www.simtable.com
1600 Lena St #D1, Santa Fe, NM 87505
office: (505)995-0206 mobile: (505)577-5828
twitter: @simtable

- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/ 
Reply | Threaded
Open this post in threaded view
|

Re: Who's on Friston? Me and my Markov Blanket

Marcus G. Daniels

A cold blooded animal or a hypothermic person is correlated to its environment, but still separate from it..

 

From: Friam <[hidden email]> On Behalf Of Stephen Guerin
Sent: Wednesday, December 2, 2020 11:53 AM
To: The Friday Morning Applied Complexity Coffee Group <[hidden email]>
Subject: [FRIAM] Who's on Friston? Me and my Markov Blanket

 

Eric Smith and Frank,

Eric,  I'd be curious what you think of Karl Friston's talk. 

 https://www.santafe.edu/events/me-and-my-markov-blanket


Perhaps better that he moved away from calling his work the "Free Energy Principle" and now using the term "Bayesian Mechanics"

 

Frank, I do find the Markov Blanket/Boundary interesting noting that it originated with Judea Pearl. Did you, Peter and Clark work with Markov Boundaries in your Causal Inference? 

 

-S

_______________________________________________________________________
[hidden email]

CEO, Simtable  http://www.simtable.com

1600 Lena St #D1, Santa Fe, NM 87505

office: (505)995-0206 mobile: (505)577-5828

twitter: @simtable


- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/ 
Reply | Threaded
Open this post in threaded view
|

Re: Who's on Friston? Me and my Markov Blanket

Frank Wimberly-2
In reply to this post by Stephen Guerin-5
Stephen,

Here's a paper.  I don't think I have a copy but I'll check my Research Gate account

PCX: Markov Blanket Classification for Large Data Sets with Few Cases

I checked and apparently a full text is available there.  Do you have a Research Gate account?  Let me know if not.

Frank

---
Frank C. Wimberly
140 Calle Ojo Feliz,
Santa Fe, NM 87505

505 670-9918
Santa Fe, NM

On Wed, Dec 2, 2020, 12:54 PM Stephen Guerin <[hidden email]> wrote:
Eric Smith and Frank,

Eric,  I'd be curious what you think of Karl Friston's talk. 
 https://www.santafe.edu/events/me-and-my-markov-blanket

Perhaps better that he moved away from calling his work the "Free Energy Principle" and now using the term "Bayesian Mechanics"

Frank, I do find the Markov Blanket/Boundary interesting noting that it originated with Judea Pearl. Did you, Peter and Clark work with Markov Boundaries in your Causal Inference? 

-S
_______________________________________________________________________
[hidden email]
CEO, Simtable  http://www.simtable.com
1600 Lena St #D1, Santa Fe, NM 87505
office: (505)995-0206 mobile: (505)577-5828
twitter: @simtable
- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/

- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/ 
Reply | Threaded
Open this post in threaded view
|

Re: Who's on Friston? Me and my Markov Blanket

Stephen Guerin-5

On Wed, Dec 2, 2020 at 1:11 PM Frank Wimberly <[hidden email]> wrote:
Stephen,

Here's a paper.  I don't think I have a copy but I'll check my Research Gate account

PCX: Markov Blanket Classification for Large Data Sets with Few Cases

Got it here. Thanks! 

- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/ 
Reply | Threaded
Open this post in threaded view
|

Re: Who's on Friston? Me and my Markov Blanket

Frank Wimberly-2
As I recall, after 20+ years, I had to implement both PCX and HITON in Java.

On Wed, Dec 2, 2020 at 1:14 PM Stephen Guerin <[hidden email]> wrote:

On Wed, Dec 2, 2020 at 1:11 PM Frank Wimberly <[hidden email]> wrote:
Stephen,

Here's a paper.  I don't think I have a copy but I'll check my Research Gate account

PCX: Markov Blanket Classification for Large Data Sets with Few Cases

Got it here. Thanks! 
- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/


--
Frank Wimberly
140 Calle Ojo Feliz
Santa Fe, NM 87505
505 670-9918


- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/ 
Reply | Threaded
Open this post in threaded view
|

Re: Who's on Friston? Me and my Markov Blanket

David Eric Smith
In reply to this post by Stephen Guerin-5
Steve, hi and thank you,

Luckily, I actually was at that talk, so didn’t have to backfill.

I don’t know what I think.  I have been aware of Karl’s work through various enthusiasts for it over the years, but there is such a firehose of volume that I wasn’t willing to start, for a “free energy principle”.  I agree that it is good he talks about inference and what I take to be causal reasoning in systems with feedbacks.

I guess I would still like to hear the answer to the question Cris Moore asks: what are you adding, Karl, beyond what Judea Pearl was already doing by putting boundary states between interiors and exteriors in Boolean networks, to define criteria of conditional independence?  I don’t know that Karl ever gave an answer to that in which I saw a crisp statement of content.

To the extent that I thought I roughly followed the talk, that particular talk seemed to be concerned with what can be said about steady states, and a kind of “holographic” manner in which the dynamics either within or outside the boundary may be encoded in timeseries of states on the boundary (the Markov blanket).  In that respect, the idea seems similar to what the Chaos Cabal back at UCSC (Farmer, Packard, Shaw, Crutchfield) did with “geometry from a timeseries”, arguing, for example, that one could reconstruct aspects of spatial structure in a turbulent flowfield from samples of velocity at a single point in space, but over extended time.  It does seem that there would need to be some kind of trapping condition: that state information not be able to flow to infinity at finite rate forever, so that eventually any states however remote would get reflected back onto the (finite, by construction) boundary.  I have not tried to think carefully about what kinds of information capacity limits should be needed for that to be possible, and it isn’t something I have ever studied from those who may know a lot about those questions.  The notion of finiteness and “reflecting back” seems similar to me, to the way total internal reflection operates in Anderson localization.  I don’t know what-all has been done to make mappings between information dynamics on Boolean networks, and continuum or peudocontinuum systems such as Anderson-localizing insulators.

I found Karl’s talk a bit frustrating; it did not have the feel of a talk that was mostly concerned with presenting a tool and putting it in the listener’s hand to understand and use.  It was again the firehose, with a sort of faux-bashful admission at the beginning that he always tries to put everything he knows into every talk, and will therefore not finish the narrative he starts.  Too many strings of notation without explaining how the reader should know what idea it was after or how that was reflected in the notation.  Having also committed that laziness in talks, I am in no position to throw stones, but listening to Karl makes me want to be more conscientious the next time I have to present something.

But maybe it’s all okay.  It may be that what he is doing establishes a useful kind of holography principle, mapping currents and state fluctuation statistics from a volume (which could perhaps be indefinitely large) back onto the finite boundaries of interiors in that volume.  If indeed the whole state space is infinite, but the information dynamics is trapping, then there should be some kind of large-deviation behavior, such as occurs in reliable coding theory, talking about how more remote volumes, carrying ever-less probability to be occupied, will take longer and longer to have their contributions to fluctuations in the overall state reflected back onto any finite boundary in the interior.

Any results of that kind, however, would probably be available only for steady states.  Dynamics would offer a variety of cases growing exponentially in the volume, and I don’t see how they could ever be tamed by projection onto a finite interior surface.  As far as I could tell, be only discussed the steady-state case in his talk.

Sorry I do not know how to answer anything of substance.  It would take a long slog through a lot of reading.  Maybe someday….  I wouldn’t want to discourage somebody else from doing it.

Eric



On Dec 2, 2020, at 2:52 PM, Stephen Guerin <[hidden email]> wrote:

Eric Smith and Frank,

Eric,  I'd be curious what you think of Karl Friston's talk. 
 https://www.santafe.edu/events/me-and-my-markov-blanket

Perhaps better that he moved away from calling his work the "Free Energy Principle" and now using the term "Bayesian Mechanics"

Frank, I do find the Markov Blanket/Boundary interesting noting that it originated with Judea Pearl. Did you, Peter and Clark work with Markov Boundaries in your Causal Inference? 

-S
_______________________________________________________________________
[hidden email]
CEO, Simtable  http://www.simtable.com
1600 Lena St #D1, Santa Fe, NM 87505
office: (505)995-0206 mobile: (505)577-5828
twitter: @simtable
- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fredfish.com%2fmailman%2flistinfo%2ffriam_redfish.com&c=E,1,WlNmm-fL7toVM7m0Cc3KF8cPe8ybYyh6V-c0qN0UH95wJ7j0OnrC-RnCLATfgwHSWRNpEuJ9Mh1JhJbCVhPjTfS9kkXW50hUJNLjfLm3c2fD&typo=1
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC https://linkprotect.cudasvc.com/url?a=http%3a%2f%2ffriam-comic.blogspot.com%2f&c=E,1,t04HZgncaezjsA8Q89fMpFvlwHT85hPOyPK3Ka9KTrUGrDd8mC37vox45lQU_3iNYTRKIJwzU7Ap7_9TY5QlqAOuq_mLL9hakbCDHAF0IL9l&typo=1


- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/ 
Reply | Threaded
Open this post in threaded view
|

Re: Who's on Friston? Me and my Markov Blanket

Steve Smith
Great conversation, to which I can add little more than a few comments
as I feel I am scrambling to "catch up", at least with the "fusion" of
multiple things I already (thought I) understood but which are
converging in this topic/discussion:

EricS wrote:

> Steve, hi and thank you,
>
> Luckily, I actually was at that talk, so didn’t have to backfill.
>
> I don’t know what I think.  I have been aware of Karl’s work through
> various enthusiasts for it over the years, but there is such a
> firehose of volume that I wasn’t willing to start, for a “free energy
> principle”.  I agree that it is good he talks about inference and what
> I take to be causal reasoning in systems with feedbacks.
>
> I guess I would still like to hear the answer to the question Cris
> Moore asks: what are you adding, Karl, beyond what Judea Pearl was
> already doing by putting boundary states between interiors and
> exteriors in Boolean networks, to define criteria of conditional
> independence?  I don’t know that Karl ever gave an answer to that in
> which I saw a crisp statement of content.
>
> To the extent that I thought I roughly followed the talk, that
> particular talk seemed to be concerned with what can be said about
> steady states, and a kind of “holographic” manner in which the
> dynamics either within or outside the boundary may be encoded in
> timeseries of states on the boundary (the Markov blanket).
I think this statement is the first time I've felt I penetrated this use
of "holographic"...  the dimensional compression as key rather than the
pervasive distribution.  As for my own understanding, I am used to
thinking in terms of the plenoptic function *with* phase.   I believe
that holographic in this context is a subdimensional (e.g. 2d
holographic plate) sampling of that field and the subsequent ability to
reconstruct a little (or a lot) about the entire full-dimensional
plenoptic field from that.    The Markov Blanket seems to be a nice
topological dual to the geometric (in holography).
>  In that respect, the idea seems similar to what the Chaos Cabal back
> at UCSC (Farmer, Packard, Shaw, Crutchfield) did with “geometry from a
> timeseries”, arguing, for example, that one could reconstruct aspects
> of spatial structure in a turbulent flowfield from samples of velocity
> at a single point in space, but over extended time.  It does seem that
> there would need to be some kind of trapping condition: that state
> information not be able to flow to infinity at finite rate forever, so
> that eventually any states however remote would get reflected back
> onto the (finite, by construction) boundary.
Thus the subdimensional sampling/collapse point above.   I think the
Chaos Cabal characterization of "geometry of timeseries" you bring up
here is related to SG's dual-field (meta) theory in formation?
>  I have not tried to think carefully about what kinds of information
> capacity limits should be needed for that to be possible, and it isn’t
> something I have ever studied from those who may know a lot about
> those questions.  The notion of finiteness and “reflecting back” seems
> similar to me, to the way total internal reflection operates in
> Anderson localization.  I don’t know what-all has been done to make
> mappings between information dynamics on Boolean networks, and
> continuum or peudocontinuum systems such as Anderson-localizing
> insulators.
Wow!  Half a dozen ideas/references triggered here...  
topological/continuum duals...

> I found Karl’s talk a bit frustrating; it did not have the feel of a
> talk that was mostly concerned with presenting a tool and putting it
> in the listener’s hand to understand and use.  It was again the
> firehose, with a sort of faux-bashful admission at the beginning that
> he always tries to put everything he knows into every talk, and will
> therefore not finish the narrative he starts.  Too many strings of
> notation without explaining how the reader should know what idea it
> was after or how that was reflected in the notation.  Having also
> committed that laziness in talks, I am in no position to throw stones,
> but listening to Karl makes me want to be more conscientious the next
> time I have to present something.
Is such a "lazy talk" not also "holographic" in the sense that the full
complexity of the ideas is projected onto a set of slides and a verbal
narrative (and a few gesticulations) for the "receiver" to reconstruct
some subset?

> But maybe it’s all okay.  It may be that what he is doing establishes
> a useful kind of holography principle, mapping currents and state
> fluctuation statistics from a volume (which could perhaps be
> indefinitely large) back onto the finite boundaries of interiors in
> that volume.  If indeed the whole state space is infinite, but the
> information dynamics is trapping, then there should be some kind of
> large-deviation behavior, such as occurs in reliable coding theory,
> talking about how more remote volumes, carrying ever-less probability
> to be occupied, will take longer and longer to have their
> contributions to fluctuations in the overall state reflected back onto
> any finite boundary in the interior.
This equivalence-of/interchangeability-with a hyper-volume to a finite
boundary (rather than a planar or similar, non-bounding) subdimensional
is the crux (I think) of what i've been ignoring in the "holographic"
metaphor in this context.   I was being (overly) literal... somehow the
complement to or contradiction-of Glen's accusation of excess meaning in
metaphors?  Maybe my overly *literal* binding *is* excess meaning in the
mapping, though I started this stream-of-consciousness with it as a
poverty-of-meaning (i.e.  a non-closed surface when a bounded surface
was required?)
>
> Any results of that kind, however, would probably be available only
> for steady states.  Dynamics would offer a variety of cases growing
> exponentially in the volume, and I don’t see how they could ever be
> tamed by projection onto a finite interior surface.  As far as I could
> tell, be only discussed the steady-state case in his talk.
This is an open (in my mind) question which I look forward to hearing
more elaboration of in this forum.
>
> Sorry I do not know how to answer anything of substance.  It would
> take a long slog through a lot of reading.  Maybe someday….  I
> wouldn’t want to discourage somebody else from doing it.
Useful to me, even if my "reflection" of what I heard here might sound
like incoherent noise.... I had to write it, even if I might not
actually hit <send> before I hit <delete>
>
> Eric

- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
FRIAM Applied Complexity Group listserv
Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
archives: http://friam.471366.n2.nabble.com/
FRIAM-COMIC http://friam-comic.blogspot.com/