Merged Artificial Intelligence Research: Supermathematics and Physics

halleyscomet said:
Do you not have enough confidence in the theory to publish it without first having proven it experimentally? Do you have some sort of moral, ethical or philosophical objection to publishing a purely theoretical paper?
Click to expand...

Bengio, a pioneer in Deep Learning can have the leisure of posting papers on major peer reviewed journals, even without any semblance of experimental results. (An example is his recent Consciousness Prior Paper)

I am not a pioneer in machine learning, nor do I have a machine learning degree, so I don't have the same leisure as Bengio.

halleyscomet said:
It occurs to me, the work needed to break your overall theory down into a project that could be executed on a grid computing platform would itself constitute a publishable paper.

You seem to have put yourself in an interesting chicken and egg situation. You’re unwilling to publish a theoretical paper but without a theoretical paper you’re unlikely to get the grants needed to purchase the hardware to do the experiments you want to do. To make progress forward you need either publish a theoretical paper or break down your theory so that it can be run on a grid computing platform.

What is your plan?
Click to expand...

That occurrence is wrong...

An initial, albeit substantial degree of the structure to be tested, shall align with the requirements I priorly mentioned here.
 
ProgrammingGodJordan said:
Bengio, a pioneer in Deep Learning can have the leisure of posting papers on major peer reviewed journals, even without any semblance of experimental results. (An example is his recent Consciousness Prior Paper)



I am not a pioneer in machine learning, nor do I have a machine learning degree, so I don't have the same leisure as Bengio.
Click to expand...


Not with that kind of self-defeating attitude.

You’re your own worst enemy.
 
abaddon said:
ProgrammingGodJordan said:
Here is Mordred's profile.

Here is one of Mordred's contributions.

Here is one of Mordred's interests.

Recall that I said Mordred deals with cosmology/particle physics. (I didn't mention Mordred had a PHD)
Click to expand...
How do you know "mordred" has a PhD? Did you simply take it on faith?
Where is Merlin's profile?
Or Lancelot's?
Or King Arthur's?

How about "My Little Pony"?
Click to expand...

What a worthless question.

I've highlighted, emboldened, underlined and coloured a relevant portion for you above.
 
Quote page 66 onward from your copy of "Geometric, Algebraic and Topological ..."

ProgrammingGodJordan said:
It's free for me....
Click to expand...
Then it is easy for you to quote page 66, etc with "more C∞(Rn) stuff " so that we do not have to guess at it being ignorance or a lie
12 October 2017: Quote page 66 onward from your copy of Geometric, Algebraic and Topological Methods for Quantum Field Theory.
We need to see in that quote "C∞(Rn)" and that this is a Euclidean superspace (the other half of your assertion).
 
halleyscomet said:
Not with that kind of self-defeating attitude.

You’re your own worst enemy.
Click to expand...

Not "self-defeating", but reality instead.

Even though my paper goes beyond papers like Bengio's by presenting a way to consider experimentation for the structure I propose to begin with, I will cannot submit on arXiv. (Its not a bad system though, as this barrier allows the reviewers to focus on papers likely to contribute well)

One needs to get recommended by somebody with a sufficient amount of papers on arXiv, before even getting the chance to submit.

One good way to get recommendation, is to show benefits over existing paradigms, in some experimental way.
 
ProgrammingGodJordan said:
Not "self-defeating", but reality instead.



Even though my paper goes beyond papers like Bengio's by presenting a way to consider experimentation for the structure I propose to begin with, I will cannot submit on arXiv. (Its not a bad system though, as this barrier allows the reviewers to focus on papers likely to contribute well)



One needs to get recommended by somebody with a sufficient amount of papers on arXiv, before even getting the chance to submit.



One good way to get recommendation, is to show benefits over existing paradigms, in some experimental way.
Click to expand...



So you’re giving up on peer review publication because one venue is not likely to accept you?

This is another reason to rework it so you can list these luminaries you keep mentioning as Co-authors. Then they can submit the paper.
 
Reality Check said:
Then it is easy for you to quote page 66, etc with "more C∞(Rn) stuff " so that we do not have to guess at it being ignorance or a lie
12 October 2017: Quote page 66 onward from your copy of Geometric, Algebraic and Topological Methods for Quantum Field Theory.
We need to see in that quote "C∞(Rn)" and that this is a Euclidean superspace (the other half of your assertion).
Click to expand...

Why bother, to expend energies there, when a prior quote of mine (as seen below) already supports my expressions?

ProgrammingGodJordan said:
RealityCheck said:
12 October 2017: A lie of "Algebraic Geometry over C∞-rings" is about Euclidean superspaces.
There is not one "superspace" in it! Iy may be a lie that the paper contains C∞(Rn) stuff unless he provides a exact citation. ProgrammingGodJordan?
Click to expand...
[IMGw=160]https://i.imgur.com/MrxleHs.jpg[/IMGw]

The C∞(Rn) stuff here, is concerned with Superalgebras, as you will see by referring to Reference 13 from the text.

Reading page 4 and onwards, you see that reference 13 (or referenced author "Carchedi") ties with Superalgebras or differentiable C∞ structures, in the neighbourhood of supersymmetry or superspace.
Click to expand...
 
Last edited:
halleyscomet said:
So you’re giving up on peer review publication because one venue is not likely to accept you?

This is another reason to rework it so you can list these luminaries you keep mentioning as Co-authors. Then they can submit the paper.
Click to expand...

That's a good idea.

Of course, that is what I am working on, as I mentioned prior to now, in a related comment here.
 
Last edited:
Covers a bit of of the same stuff as the existing Genius Edward Witten, could he help to intensify artificial intelligence research? thread.

Physicists in general do not need to study consciousness. There is little need to study consciousness in order to measure the current through a wire!
Some physicists think about whether consciousness has a role in physics.

Ditto for AI. Some physicists research AI and may use tools from physics to do so, e.g. want to use quantum computers. Most physicists do not need to study AI because it has no relevance to their research.

It is irrelevant that manifolds are "central to physics and mathematics".

One paper using the word manifold two times in the context of data does not make the manifolds from math or physics "quite prevalent" anywhere in AI.
Disentangling factors of variation in deep representations using adversarial training
interpolation: to evaluate the coverage of the data manifold, we generated a sequence of images by linearly interpolating the codes of two given test images (for both specified and unspecified representations);
Click to expand...
Thus, 3(b) shows a reasonable coverage of the manifold with some abrupt changes.
Click to expand...
Plus the reference
[24] Scott Reed, Kihyuk Sohn, Yuting Zhang, and Honglak Lee. Learning to disentangle factors of variation with manifold interaction. In Proceedings of the 31st International Conference on Machine Learning (ICML-14), pages 1431–1439, 2014.
Click to expand...

Simply put: Those physicists who need or want to to study consciousness or AI, are studying consciousness or AI.
 
Last edited:
Reality Check said:
There is little need to study consciousness in order to measure the current through a wire!
Click to expand...

I don't know if how current flows through a wire can help to describe the conscious observer.

Reality Check said:
Some physicists think about whether consciousness has a role in physics.

Ditto for AI. Some physicists research AI and may use tools from physics to do so, e.g. want to use quantum computers. Most physicists do not need to study AI because it has no relevance to their research.
Click to expand...

Redundant, if you actually watched Tegmark's video, you would quickly find out that he is encouraging his physicist colleagues to study consciousness, so this means not surprisingly, that whether consciousness has a role in physics is questionable, particularly, among physicists. (especially his physicist colleagues)
However, some common sense tells that if you think about it logically, consciousness, that is the mechanism which allows the observer to achieve complex goals in a general learning manner, i.e. general intelligence, is reasonably nothing but some information driven process, bounded by the laws of physics, and thereafter, not surprisingly applicable in physics...
 
Reality Check said:
It is irrelevant that manifolds are "central to physics and mathematics".

One paper using the word manifold two times in the context of data does not make the manifolds from math or physics "quite prevalent" anywhere in AI.
Disentangling factors of variation in deep representations using adversarial training
Click to expand...

[IMGw=260]https://i.imgur.com/MrxleHs.jpg[/IMGw]

That paper was merely a sample from much work being done regarding manifolds.

Here is a tip. When you see "disentangling factors" in relation to machine learning you are in the world of manifold learning.


Early Visual Concept Learning with Unsupervised Deep Learning, (June 2016)

Exponential expressivity in deep neural networks through transient chaos, (June 2016)

Disentangling factors of variation in deep representations using adversarial training, (November 2016)

...


Footnote:

[IMGw=400]https://i.imgur.com/58zzIPo.png[/IMGw]

It is not "irrelevant" that manifolds are central to physics and mathematics.
That physicists may work with these things, is quite relevant if they are to utilize this properties to study consciousness/artificial general intelligence.

Manifolds may afford models degrees of freedom (learning position, scale, size, etc), in temporal difference scenarios.

Edited by Loss Leader: 
Edited IMG tags to IMGW. Overly large images are disruptive.
 
Last edited by a moderator:
RealityCheck said:
Simply put: Those physicists who need or want to to study consciousness or AI, are studying consciousness or AI.
Click to expand...

Yes, what you express above may likely be simply, but crucially, wrongly put.

[IMGw=160]https://i.imgur.com/KjmpRRu.png[/IMGw]

As Max Tegmark expressed in a youtube video here, physicists have long neglected to define the observer in much of the equations, and he particularly refers to the instance that not analyzing consciousness may be a giant obstacle in the aims of further non trivially unraveling the laws of physics.
 
John Jones said:
I'm not taking your word for it or anything else due to your inferior command of English. Can you think of any reason I should?
Click to expand...

[IMGw=260]https://i.imgur.com/4fCD9XZ.jpg[/IMGw]

Odd, I don't have these long standing English debates with people of high intellect, such as Bengio or people who deal with cosmology/particle physics.

Anyway, take a look at Max's video here, or buzz off instead, your choice.

Listen to his words, and ignore mine if you shall so desire.


Footnote:
The word "huh" or no response at all, shall be relegated to any further discussions about English of yours.
 
Cite the definition of disentangling factors that states that it always has manifolds

ProgrammingGodJordan said:
...inane image, etc. snipped...
That paper was merely a sample from much work being done regarding manifolds.
Click to expand...
Read my post again. That was an irrelevant paper because there were no manifolds from math or physics in it, just a "data manifold".

Checked the next paper and you are wasting everyone's time - no mention of manifolds and an unsupported assertion:
12 October 2017: Cite the definition of disentangling factors that states that it always has math or physics manifolds in it.

ETA:
A thing being central to field A does not automatically make it central to another field. Physicists may work with the statistics of bosons and fermions so:
12 October 2017: Cite the use of Fermi or Bose statistics "to study consciousness/artificial general intelligence" :p!
 
Last edited:
Reality Check said:
Read my post again. That was an irrelevant paper because there were no manifolds from math or physics in it, just a "data manifold".

Checked the next paper and you are wasting everyone's time - no mention of manifolds and an unsupported assertion:
12 October 2017: Cite the definition of disentangling factors that states that it always has math or physics manifolds in it.
Click to expand...

The things I stroke through above, stemmed from your ignorant highlighted statement.

Note that I didn't say that if you were disentangling factors, you were only in the world of manifolds.

Most importantly, in those papers, it is clear that manifolds are being discussed, some key give aways are mentions of "manifolds", and "disentangling factors" or "disentangling" or "disentangled".

ProgrammingGodJordan said:
Early Visual Concept Learning with Unsupervised Deep Learning, (June 2016)

Exponential expressivity in deep neural networks through transient chaos, (June 2016)

Disentangling factors of variation in deep representations using adversarial training, (November 2016)

...
Click to expand...
 
Last edited:
Reality Check said:
A thing being central to field A does not automatically make it central to another field. Physicists may work with the statistics of bosons and fermions so:
12 October 2017: Cite the use of Fermi or Bose statistics "to study consciousness/artificial general intelligence" :p!
Click to expand...

I don't detect fermi usage, in agi...

[IMGw=180]https://i.imgur.com/rp1IMhq.jpg[/IMGw]

But one shouldn't be quick to call things immutably separate, there were probably people who just didn't detect the correlation between things such as mean field theory and machine learning. (Mean field theory in machine learning paper here)
 
Last edited:
ProgrammingGodJordan said:
Max Tegmark, probably has a better grasp than you on this topic, and as Max Tegmark expressed in a youtube video here, physicists have long neglected to define the observer in much of the equations. (The observer being the intelligent agent)
Click to expand...

With no offense. why should they? Their purpose by their choice is to study real physics, not the brainwaves of those who do the actual work of physicists.

On the bright side, you may want to get with Kumar on this and related.
 
ProgrammingGodJordan said:
[IMGw=260]https://i.imgur.com/MrxleHs.jpg[/IMGw]

That paper was merely a sample from much work being done regarding manifolds.

Here is a tip. When you see "disentangling factors" in relation to machine learning you are in the world of manifold learning.


Early Visual Concept Learning with Unsupervised Deep Learning, (June 2016)

Exponential expressivity in deep neural networks through transient chaos, (June 2016)

Disentangling factors of variation in deep representations using adversarial training, (November 2016)

...


Footnote:

[qimg]https://i.imgur.com/58zzIPo.png[/qimg]

It is not "irrelevant" that manifolds are central to physics and mathematics.
That physicists may work with these things, is quite relevant if they are to utilize this properties to study consciousness/artificial general intelligence.

Manifolds may afford models degrees of freedom (learning position, scale, size, etc), in temporal difference scenarios.
Click to expand...

Not really.....hope that helps - and leads you away from distractions!!!
 
@Realitycheck
[IMGw=180]https://i.imgur.com/0SKFCTP.png[/IMGw]

Although Max Tegmark could be wrong on this; I may not research directly more on the matter of consciousness' requirements in physics, but instead physics' requirement in developing artificial consciousness, i.e. I shall focus on striving to contribute to the development of artificial general intelligence, which is probably guaranteed to be a type of meta solution to much of humanity's issues, including illness diagnosis or medicine development and the advancement of the rate of physics experimentation ...
 
ProgrammingGodJordan said:
..........However, some common sense tells that if you think about it logically, consciousness, that is the mechanism which allows the observer to achieve complex goals in a general learning manner, i.e. general intelligence, is reasonably nothing but some information driven process, bounded by the laws of physics, and thereafter, not surprisingly applicable in physics...
Click to expand...

Applicable in physics, sure. A subject for study by physicists? Well that isn't so clear-cut. Science divides itself up into smaller and smaller specialities, and so there are experts in consciousness and others in artificial intelligence whose work may be of interest to physicists.......without it being necessary or even productive for non-specialists (including physicists) to do the work themselves.
 
ProgrammingGodJordan said:
...snipped inane image...
Although Max Tegmark could be wrong on this; I may not research directly more on the matter of consciousness' requirements in physics, but instead physics' requirement in developing artificial consciousness...
Click to expand...
Max Tegmark could be right or wrong because this his opinion, i.e. not textbook or consensus physics. But if you do not want to learn what he said the why cite it?
Why does deep and cheap learning work so well? is not about any physics requirement
We show how the success of deep learning could depend not only on mathematics but also on physics: although well-known mathematical theorems guarantee that neural networks can approximate arbitrary functions well, the class of functions of practical interest can frequently be approximated through "cheap learning" with exponentially fewer parameters than generic ones. We explore how properties frequently encountered in physics such as symmetry, locality, compositionality, and polynomial log-probability translate into exceptionally simple neural networks. We further argue that when the statistical process generating the data is of a certain hierarchical form prevalent in physics and machine-learning, a deep neural network can be more efficient than a shallow one. We formalize these claims using information theory and discuss the relation to the renormalization group. We prove various "no-flattening theorems" showing when efficient linear deep networks cannot be accurately approximated by shallow ones without efficiency loss, for example, we show that n variables cannot be multiplied using fewer than 2^n neurons in a single hidden layer.
Click to expand...
This is about efficiency.
 
Reality Check said:
Max Tegmark could be right or wrong because this his opinion, i.e. not textbook or consensus physics. But if you do not want to learn what he said the why cite it?
Why does deep and cheap learning work so well? is not about any physics requirement

This is about efficiency.
Click to expand...

And what makes you think efficiency and Physics are separate?

Anyway consider this quote from the paper:

"We explore how properties frequently encountered in physics such as symmetry, locality, compositionality, and
polynomial log-probability translate into exceptionally simple neural networks."

"We further argue that when the statistical process generating the data is of a certain hierarchical form prevalent in physics and machine-learning, a deep neural network can be more efficient than a shallow one.

We formalize these claims using information theory and discuss the relation to the renormalization
group" .

So, it is about physics.. Did you actually read more than O(log(n)) of the paper?
 
Last edited:
MikeG said:
Applicable in physics, sure. A subject for study by physicists? Well that isn't so clear-cut. Science divides itself up into smaller and smaller specialities, and so there are experts in consciousness and others in artificial intelligence whose work may be of interest to physicists.......without it being necessary or even productive for non-specialists (including physicists) to do the work themselves.
Click to expand...

Refer to my following quote:

ProgrammingGodJordan said:
@Realitycheck
[IMGw=180]https://i.imgur.com/0SKFCTP.png[/IMGw]

Although Max Tegmark could be wrong on this; I may not research directly more on the matter of consciousness' requirements in physics, but instead physics' requirement in developing artificial consciousness, i.e. I shall focus on striving to contribute to the development of artificial general intelligence, which is probably guaranteed to be a type of meta solution to much of humanity's issues, including illness diagnosis or medicine development and the advancement of the rate of physics experimentation ...
Click to expand...
 
Reality Check said:
12 October 2017: Cite the use of Fermi or Bose statistics "to study consciousness/artificial general intelligence" :p!
Manifolds being used in physics does not automatically mean that they can be used in consciousness/artificial general intelligence. That is why there is the manifold hypothesis (not theory or mechanism. etc.)

More seriously
12 October 2017: Cite the definition of disentangling factors that states that it always has math or physics manifolds in it.
Click to expand...

You need to cite where I supposedly used the word "always" as you claimed above.

Also, refer to this.
 
Three threads about similar topics in artificial intelligence research have been merged. Any discussion of these or related topics should be confined to this thread. Starting new threads may incur further mod action. If you are unsure whether a post should go here or in a new thread, please PM the moderating team. Thank you.
Posted By: Loss Leader
 
You must log in or register to reply here.

Back
Top Bottom