I want to crack Neural Networks

  • 55 Replies
  • 1990 Views
*

korrelan

  • Trusty Member
  • *********
  • Terminator
  • *
  • 836
  • Look into my eyes! WOAH!
    • Google +
Re: I want to crack Neural Networks
« Reply #30 on: January 15, 2018, 10:15:57 pm »
Your first picture shows a convolutional network.  The detected line features are fed through a max pooling network/ layer.  The pooling layer is just a way to keep the values/ vectors within reasonable bounds before being fed into the next layer.  The pooling layer also usually shrinks the detected image features, with no loss of detail.

There are many variations on the CNN schema, some pool features into larger features (eyes, nose, etc). Usually only at the end of the CNN chain of networks/ processes are the detected features fed into a fully connected network (FCN).  The full set of detected line features are never actually recombined into the original image.  The FCN (last stage) is where the machine learns to name an object from the features present in the image; all the stages prior to the FCN are just used to extract recognisable features from the image.

Your second picture is of a standard feed forward classifier, very similar to the FCN mentioned earlier.  This is a totally different method of using a NN to detect features/ numbers, the image matrix of pixels is fed in and the NN learns to classify a output.  This method is not usually as versatile/ accurate as the CNN approach but requires less processing.

Keep in mind that there is no silver bullet solution, there are thousands of different variations on the NN, CNN, RNN, architectures.

ED: OMG close some of those tabs on the browser... my OCD is twitching lol

 :)
It thunk... therefore it is!

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1208
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: I want to crack Neural Networks
« Reply #31 on: January 15, 2018, 11:34:23 pm »
I actually got my amount of open work-tabs down recently. However my knowledgebase is a little scarier to look at. Good thing I know where everything is.

So IF the filtered feature images DID get layered back as one, it would sorta ruin the whole point of the filters right?, however it would mean there is actual faces higher up in the network, lol. While if the filtered feature images DON'T get layered back as one, then the purpose of the filters is kept alive right?, however there is no actual faces in higher layers, rather they are there but as encryption-like and are detected by the fully-connected layer of weights with the lines voting in by however they were trained right? Also, after the first layer of filters, the lines/curves/etc features filtered are the only things that um, have an appearance, I mean, when a nose etc is detected and then a face is detected, these things detected will never have an appearance right, they are only an encryption and weight votings right? Cus I was thinking that the detected lines/curves would become shapes, and then higher, hehe...

If I stare at a human's face, I will detect "face" at the end of the network. But, why and how am I able to concentrate on just the nose and see the nose? If the encryption for "nose" "I see a nose I see a nose" is in a layer behind the "face" layer, then, that means it would need to stop there, and output a layer early, right? Also my concentration gives more score to that area I guess.

Is korrelan working hard on Deep Sensory Cortices because that will pave the way for the rest? Like The Deep Motor Cortex?

Btw it's bugging me so I wanted to make it clear, I know korrelan, you are the father of wisdom with the ANN / machine learning.

In the brain there is sensory cortices and the motor cortex. Why does Machine Learning have no Motor Cortex ANN algorithms????? For example, take CNNs, or Logistic Regression, or HHMMs, they are not motor cortexes in the sense of the human brain's motor cortex. Why does it seem Machine Learning is focusing on "senses" but not "motor actions" ?!?!? I know I've seen Machine Learning projects have spiders learn to crawl BUT, never mention the motor cortices, only the ex. CNN. Half the story is missing. Omg guys.
« Last Edit: January 16, 2018, 06:06:25 pm by LOCKSUIT »
Emergent

*

keghn

  • Trusty Member
  • *********
  • Terminator
  • *
  • 777
Re: I want to crack Neural Networks
« Reply #32 on: January 19, 2018, 04:29:45 pm »

Neural Networking: Robots Learning From Video: 
https://hackaday.com/2018/01/18/neural-networking-robots-learning-from-video/ 


*

WriterOfMinds

  • Trusty Member
  • ***
  • Nomad
  • *
  • 87
    • WriterOfMinds Blog
Re: I want to crack Neural Networks
« Reply #33 on: January 19, 2018, 06:45:56 pm »
I wonder if we don't have separate detection networks for faces and for individual parts of faces. I'll illustrate why I think so.

Let's say there are two dots on a piece of paper. When you look at them, all your brain probably registers is "two dots." But if you add a curved line underneath the dots, suddenly you see a (highly simplified) face. Nothing about the dots themselves tells you that they are eyes, but once you see the face, you can infer that the dots are eyes. So the detection of eyes, as such, cannot be a prerequisite for detection of a face. It's possible to detect an eye that isn't part of a face, but in that case you need more detail -- an eye-shaped outline, an iris, a pupil. So I think that "I see an eye" is not necessarily a previous layer of "I see a face." It could be its own separate thing.

*

keghn

  • Trusty Member
  • *********
  • Terminator
  • *
  • 777
Re: I want to crack Neural Networks
« Reply #34 on: January 19, 2018, 07:10:20 pm »
 There is a law of pattern recognition that i have not found. Or i will have to make to explain such things. Like having
a object such as a dot that is only 10 percent a eye, line that ha only 10 percent of the features of a mouth. But when place
right orientation to one and another it is 99 percent a face. 


*

ivan.moony

  • Trusty Member
  • *********
  • Terminator
  • *
  • 869
  • Smile, it's another day!
    • Structured Type System
Re: I want to crack Neural Networks
« Reply #35 on: January 19, 2018, 07:12:33 pm »
Of course, correlation between recognizable objects is also important for overall recognition process. Recognizing a whole face takes n specific parameters, while each of those parameters, taken as a single unit, grows up possible recognition set. For example, when you see the whole face, dot can stand only for an eye, while taken in isolation, a dot can stand for an eye, a teardrop, a mold, or a star. The bigger the possible matching set is, I think it is harder to actually tell what the thing is. And the sets shrink in correlation with other parameters.
« Last Edit: January 19, 2018, 09:03:15 pm by ivan.moony »
Did you notice that today is the first day of the rest of your life?

*

keghn

  • Trusty Member
  • *********
  • Terminator
  • *
  • 777
Re: I want to crack Neural Networks
« Reply #36 on: January 19, 2018, 11:09:05 pm »
 I going with object outline regression algorithm to change the face objects to a lower dimension. Then with the lower dimension
object pair them with a physical distance weight and morph weight. Then this well work. NN do this will. And with
a also with a secret of analog "OR" operation.

 

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1208
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: I want to crack Neural Networks
« Reply #37 on: January 20, 2018, 01:44:22 am »
WriterOfMinds....um.............If you take a blank sheet of paper and a pencil, and draw 2 small circles, and a wide curve, you can see a face, and, if you look differently at it (without moving your head or paper) you can see a wide curve.

SO...
This means our layers must be like this!:

input layer
hidden layer
hidden layer
curve detecting layer --- I can be an output layer too
face detecting layer --- I am the last/output layer, face detected
output layer

See attachment too.

Hey wait, isn't there columns like my picture in the brain? Maybe a bi-directional?
https://www.google.ca/search?q=neural+columns&source=lnms&tbm=isch&sa=X&ved=0ahUKEwiGvZPGt-XYAhUW82MKHcv3DNcQ_AUICigB&biw=1280&bih=879#imgrc=8PGBppipVcy9MM:
Emergent

*

keghn

  • Trusty Member
  • *********
  • Terminator
  • *
  • 777
Re: I want to crack Neural Networks
« Reply #38 on: January 25, 2018, 11:30:15 pm »

Convolutional Neural Networks Learn Class Hierarchy?: 


https://vimeo.com/228263798 


*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1208
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: I want to crack Neural Networks
« Reply #39 on: January 26, 2018, 03:17:02 am »
Wicked. Even better CNNs. However I want to make it clear that my goal is to understand the whole human brain from the top level, slowly going top-down.
Emergent

*

keghn

  • Trusty Member
  • *********
  • Terminator
  • *
  • 777
Re: I want to crack Neural Networks
« Reply #40 on: January 27, 2018, 03:53:46 pm »

Autoencoder Explained: 

   

*

keghn

  • Trusty Member
  • *********
  • Terminator
  • *
  • 777
Re: I want to crack Neural Networks
« Reply #41 on: January 28, 2018, 02:49:22 pm »

*

Art

  • At the end of the game, the King and Pawn go into the same box.
  • Global Moderator
  • *******************
  • Prometheus
  • *
  • 4700
Re: I want to crack Neural Networks
« Reply #42 on: January 28, 2018, 05:27:49 pm »
Wicked. Even better CNNs. However I want to make it clear that my goal is to understand the whole human brain from the top level, slowly going top-down.

In that case, I hope you have a very long lifespan as people have been trying to understand the human brain for an extremely long period of time and are still only scratching the surface. Good luck!

To quote Mr. Emerson M. Pugh - "If the Human Brain Were So Simple That We Could Understand It, We Would Be So Simple That We Couldn’t."
In the world of AI, it's the thought that counts!

*

ranch vermin

  • Not much time left.
  • Replicant
  • ********
  • 568
  • Its nearly time!
Re: I want to crack Neural Networks
« Reply #43 on: January 28, 2018, 05:30:13 pm »
as far as we "true lifers" go,  we can say ANYTHING is ANYTHING, you can look at a dog how its a man,  we are beyond ai systems, we are true intelligence as far as we know...  maybe god knows things that we cant concieve.

But Onto this feature hierarchy thing ->

Say I had every possible photo of a nose,  and I had every possible photo of an eye,    the individual photos are *anded* as a single photo but to make the class they are an *or*,   any one photo of the nose i then activate the class nose.  having it *or* the photos offers reusable compression.  (layers of features is very similar to what im saying.)  because they all arise at the same group in the end - so i can share bits and pieces that *or simplify* together,  which is similar to having features (or levels in an NN),  except im taking it from a *boolean logic simplification* standing point.

Locksuit,  theres motor stuff around, korrellan has a video on it,  theres plenty on the internet,  whats different and new would be someone taking one of these vision systems and having it as a world for the motor cortex to explore.  (its combining them thats the exciting thing on its way...)

Then well see some pretty hectic stuff come out.  >XD


[EDIT]
theres a thing called geometric invarience,  where just one 1024 bit or so key will automatically respond to a huge camera difference around the object.  and that saves ram hugely over just a photo orrery by itself.

Look up brisk orb, or sift or surf descriptors,  they are pretty amazing and useful.
[/EDIT]

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1208
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: I want to crack Neural Networks
« Reply #44 on: January 31, 2018, 02:46:23 am »




This guys clearly doing a Korrelan "thing" here.


OMG OMG OM G OMG OMG look!


moreee neurons


MOREEEE


Even more neuronssssssss!!


omg so good...i liked the part around 5:00

"I think, therefore I am"

also new diagram attached....I'm gonna make a better one soon hehe
« Last Edit: January 31, 2018, 08:22:50 pm by LOCKSUIT »
Emergent

 


Young Alpha
by 8pla.net (Bot Conversations)
Today at 01:56:11 am
Emergence of the universe's PURPOSE !!!!
by keghn (Future of AI)
February 19, 2018, 04:54:20 pm
XKCD Comic : 2018 CVE List
by Tyler (XKCD Comic)
February 19, 2018, 12:01:26 pm
the emergence of AI
by LOCKSUIT (Future of AI)
February 19, 2018, 05:04:07 am
Robot Vacuum Cleaners
by tekchamps (General Robotics Talk)
February 18, 2018, 06:10:53 pm
The last invention.
by LOCKSUIT (General Project Discussion)
February 17, 2018, 11:51:20 pm
Supervised AGI
by keghn (General AI Discussion)
February 16, 2018, 08:24:24 pm
Strange learning curves
by Kaeldric (AI Programming)
February 16, 2018, 06:28:14 pm

Users Online

31 Guests, 1 User
Users active in past 15 minutes:
keghn
[Trusty Member]

Most Online Today: 51. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)

Articles