Ai Forums Home Welcome Guest    Monday, May 22, 2017
Ai Site > Ai Forums > The Artificial Intelligence Forum > ANN Brain 2016 Last PostsLoginRegisterWhy Register
Topic: ANN Brain 2016

keghn
posted 6/11/2016  23:03Send e-mail to userReply with quote
Artificial Neural Network Brain

The center of it all is the consciousness part. Which are artificial neuron
daisy chained together.
A spark jump from one artificial neuron to the next. This spark moves
through the daisy chain at the same rate of life. Like watching a movie
video of life that is on play. Not fast forward, not on slow or on
reversed speed.
When the spark enters into the next neuron it send a pulse to The Main
Auto Encoder Artificial Neural Network. Which is the main sequential
memory storage.
A pulse coming off the daisy chain moves the video to the next
frame of life.
All of these video frame of life are stored in weight space matrix.

The daisy chain neuron take in a second input. They are pulses from
a Perceptron Artificial Neural Network that detects object, backgrounds,
and sub features. if these thing are being detected, then a minor
pulse will enter into daisy chain neuron.
The sprack
traveling in the daisy chain of neuron will be re enforced.
If the spark is not re-enforced it will fade out.
Detection by the perceptron neural network will can cause a new spark
to start up somewhere else on this extremely long daisy chain of neurons.

The daisy chain neuron has two input and two outputs.
Inputs are from the daisy chain before it and input from perceptron
neural networks.
The outputs are the one going to the next daisy chain neuron and the
other output goes to the Main Auto Encoder Neural Network.





AiHasBeenSolved
posted 6/13/2016  00:46Send e-mail to userReply with quote
We can build an AI in 2016.

AI is a lot simpler than Netizens think it is.

True AI is not instantly mature with human-level intelligence, but needs to grow as a human child grows.

What AI needs most is a theory of mind.

http://ai.neocities.org/AiSteps.html

 Mentifex

keghn
posted 6/15/2016  18:27Send e-mail to userReply with quote


Look, the elite are poaching my work:
http://www.eurekalert.org/pub_releases/2016-06/cp-hi060716.php

aristocrats in action

  aristocrats in action

rouncer
posted 6/16/2016  06:17Send e-mail to userReply with quote
Hey Keg - I reckon meshes are NOT to be used for anything except for hypothetical reasons - the real deal has to be alot more optimized are hardware/software wise, where a mesh (an actual cell network), unless it was in its perfect hardware situation, its not very optimal for your pc to run it.

And not only that, the amount of connections they need, as well as them having to generate connections as they go... make them worthless to make in hardware as well.

But they are still possible to make, I wouldnt say mr magic man couldnt do it if he thought hard enough about it.

But... it would have to be something zany, like conductance that grows like a slime mould maybe? But there still could be a use for them.


[EDIT] sorry for glance reading... im a wanker.



From what you said, I gather that you have a feature entry, and a storage system?

If thats right- how do u generate your behaviour. u could by copying the features coming in.


Last edited by rouncer @ 6/16/2016 2:30:00 PM

keghn
posted 7/4/2016  16:01Send e-mail to userReply with quote


In honor of Rosalind Franklin i must hide my work now.
Those brits are scum,

  1  
'Send Send email to user    Reply with quote Reply with quote    Edit message Edit message

Forums Home    Hal and other child machines    Alan and other chatbots    Language Mind and Consciousness  
Contact Us Terms of Use