Super Artificial Intelligence, a naive approach

[ProgrammingGodJordan]

See my earlier post for the use of rectal excavation in the construction of artificial profundity.

Your prior post was absent non worthless content.

Still, you need see DeepLearningBook by Bengio et al.
(Where the categories you claimed I made up, are discussed briefly there)




Footnote:
At some point, everything is probably made up.

 

[MikeG]

Your prior post was absent non worthless content.

Still, you need see DeepLearningBook by Bengio et al.
(Where the categories you claimed I made up, are discussed briefly there)

Footnote:
At some point, everything is probably made up.

Good god, PGJ, do you read this stuff through before you hit "submit". This is the worst form of buggerised English it's possible to think of. Just speak normally.

 

[MikeG]

See the deep learning book by Yoshua Bengio et al, for overview of computational neuroscience vs deep learning.

Firstly, link to it if you want anyone to take a look. Secondly, I previously asked you where this "deep learning" notion came from, and you answered facetiously and sneeringly, rather than give this reference. Why was that?

 

[Beelzebuddy]

Your prior post was absent non worthless content.

Then perhaps you should reevaluate your concept of worth.

Still, you need see DeepLearningBook by Bengio et al.

No I don't. I already use deep learning. It has no resemblance at all with how the brain works, nor is it meant to have any.

Footnote:
At some point, everything is probably made up.

An old philosophical position known as solipsism, itself derived from the words "solo" and "priapism."

Secondly, I previously asked you where this "deep learning" notion came from, and you answered facetiously and sneeringly, rather than give this reference.

Do you mean the concept itself, or its comparison to the human brain? I can teal deer you on it's history if you'd like, it's really a fascinating algorithm.

But if you meant the latter, I believe PGJ is falling into the common woo trap of juxtaposing independent concepts on the basis of trivial relationships. Same reason people like to think everything with the word "quantum" is somehow intextricably intertwined with everything else that uses it.

 

[ProgrammingGodJordan]

Firstly, link to it if you want anyone to take a look. Secondly, I previously asked you where this "deep learning" notion came from, and you answered facetiously and sneeringly, rather than give this reference. Why was that?

After you accused me of making up categories, I answered with a link in reply 430.

 

[ProgrammingGodJordan]

Then perhaps you should reevaluate your concept of worth.


No I don't. I already use deep learning. It has no resemblance at all with how the brain works, nor is it meant to have any.


An old philosophical position known as solipsism, itself derived from the words "solo" and "priapism."


Do you mean the concept itself, or its comparison to the human brain? I can teal deer you on it's history if you'd like, it's really a fascinating algorithm.

But if you meant the latter, I believe PGJ is falling into the common woo trap of juxtaposing independent concepts on the basis of trivial relationships. Same reason people like to think everything with the word "quantum" is somehow intextricably intertwined with everything else that uses it.

This prior quote applies:

Well, there are two classes of brain based learning:

(1) Deep learning(a) This began by using hints from neuroscience.
(b) However, deep learning benefits from paradigms outside of neuroscience.
(c) This is because deep learning experts don't know enough about the brain, to get much performance.



(2) Computational neuroscience(a) Stricter versions take a path to as closely as possible, attempt to imitate brain neurobiology, unlike Deep Learning. (example is Markram's project)
(b) Mixture of computational neuroscience and deep learning both attempts to imitate the brain, while adapting deep learning tasks completion. (Example IBM)



.

 

[Beelzebuddy]

This prior quote applies:

No it does not. It is wrong.

 

[fuelair]

It's something he made up.

But did not make up well!!!!!!!

 

[Reality Check]

@Reality Check

@ProgrammingGodJordan what looks like fantasies about "super manifolds" on an inaccessible google drive looks like a waste of time.
Especially since you seem to be arguing form a stance of ignorance:
20 March 2017 ProgrammingGodJordan: Do you know that a computer simulation is not a human being? (i.e. computer simulations do not have the speed of brains)
20 March 2017 ProgrammingGodJordan: Cite a Moore's law explicitly for computer simulations.

 

[Reality Check]

For people who are interested in the actual manifold hypothesis here is an nice blog article: Neural Networks, Manifolds, and Topology.

 

[ProgrammingGodJordan]

No it does not. It is wrong.

What in particular is "wrong" from reply 446?

 

[ProgrammingGodJordan]

For people who are interested in the actual manifold hypothesis here is an nice blog article: Neural Networks, Manifolds, and Topology.

You pointed out a reference used in my supermanifold hypothesis (via deep learning).

To get an even better understanding of manifolds with respect to deep learning, also see DeepLearningBook by Yoshua Bengio et al.



Footnote:
You can view the pdf without downloading it here: https://www.academia.edu/31926696/Supermanifold_Hypothesis_via_Deep_Learning_

 

[abaddon]

You pointed out a reference used in my supermanifold hypothesis (via deep learning).

To get an even better understanding of manifolds with respect to deep learning, also see DeepLearningBook by Yoshua Bengio et al.



Footnote:
You can view the pdf without downloading it here: https://www.academia.edu/31926696/Supermanifold_Hypothesis_via_Deep_Learning_

I must concede, your thread title is apropos.

 

[ProgrammingGodJordan]

I must concede, your thread title is apropos.

Indeed

 

[abaddon]

Indeed

You agree your approach is naive. OK.

 

[ProgrammingGodJordan]

You agree your approach is naive. OK.

Yes, as indicated in the title: 'Super Artificial Intelligence, a naive approach.."

 

[abaddon]

Yes, as indicated in the title: 'Super Artificial Intelligence, a naive approach.."

Great. We agree that your approach is naive. Now, why should anyone give any credence to such naivete?

 

[fagin]

Indeed

He said it...

 

[Beelzebuddy]

What in particular is "wrong" from reply 446?

Almost everything. Let's start with the first sentence:

Well, there are two classes of brain based learning:

No there are not. There are either zero or lots and lots of them, depending on whether by "brain based learning" you mean algorithms that operate in the same manner as the brain, or algorithms that people say operate in the same manner as the brain.

If you mean the former, there are none, although the Human Brain Project (the current offshoot of Markram's work, he's since dived back into biology) gets half credit for trying to do it right instead of half-assing it long enough to put out a press release.

But if you meant people who half-ass it enough to put out a press release about how their system is "inspired by" the human brain, you'll have a line out the door. And all of them are crap.

Deep learning is in neither of these categories. Any comparisons to brain function are red herrings generated by people who don't understand why it is what it is or how it does what it do.


For the peanut gallery, the book PGJ keeps referencing is online here, and appears to lack all the woo that keeps cropping up in his posts. A relevant snippet from the introduction:

While the kinds of neural networks used for machine learning have sometimes been used to understand brain function (Hinton and Shallice, 1991), they are generally not designed to be realistic models of biological function.

 

[ProgrammingGodJordan]

Great. We agree that your approach is naive. Now, why should anyone give any credence to such naivete?

Perhaps...