Recent Posts

Pages: [1] 2 3 ... 10
1
General Software Talk / Looking for custom software development company
« Last post by Billdoor on Today at 10:20:36 am »
For quite a long time I have an idea of great app based on mobile augmented reality. Recently I've found investors who're ready to cover all the expenses.
So the question is stated above. If you have a good agency of developers lined up, please share.
2
Human Experience and Psychology / Is free will reproducible?
« Last post by Zero on Today at 09:12:17 am »
My first idea was to name this thread "What is free will?"... but wondering whether free will is reproducible seems to be more pragmatic, and still includes the question of what it is.

I remember WriterOfMind saying that free will could be somehow related to "localized temporary override of the standard laws of physics", a brave suggestion. Well, do you think that such "overriding" exists? If so, is it reproducible? Why or why not?

Do you think human free will is an illusion? Do you think it's real? If it's an illusion, should an AGI have the same illusion? If it's real, then what is it? How do we reproduce it?

What's your take on these topics?
3
General Project Discussion / Re: The last invention.
« Last post by Zero on Today at 08:55:11 am »
Thank you! Your explanations are very clear.

Can it act? Does it feel pleasure and pain? Do you plan to connect it to minecraft for example?

4
2^(2^1024.)

something even quantum computers cant solve.   you only get one log,  and that only removes one 2.   u need 2 quantum computer tricks at once to get that number.
5
UltraHal / Ultra Hal 7 - Release Candidate
« Last post by Art on Today at 01:35:03 am »
Zabaware has put forth its Release Candidate at this time. All seems to be functioning quite nicely and if it continues to do so within the next few days then it will become the Final Release. I believe the word is Robert would like to have it for you before Christmas.

The cost and Discount is explained on the Zabaware site because I certainly don't wish to mis-quote anything here.

http://www.ultrahal.com/community/index.php?topic=14090.0
6
General Project Discussion / Re: The last invention.
« Last post by korrelan on Today at 12:13:09 am »
Quote
How do you know it's not just noise? The whole thing I mean, not only the second GTP. What intelligence does the whole connectome show?

Hmmm… that’s a very good question… prepare for a long winded answer lol.

I presume you have read my project page and have an idea of what I’m trying to achieve.  I’m back engineering the human brain, looking for a single AGI solution based on the human nervous system that makes every other narrow AI obsolete… a machine at least equivalent to us.

Ok... It depends on your definition of intelligence (don’t sigh lol), and the level of abstraction you are looking for intelligence, or the root/ cause of intelligence.  An ant colony shows ‘intelligent’ behaviour where as a single ant does not, so from this point of view intelligence is a group/ collective/ compound behaviour. Slime mould also acts ‘intelligently’ but again it’s just a collection of single celled organisms.  There is some kind of innate/ emergent intelligence that these simple organic systems are leveraging.

That’s basically what my project is about. 

I’ve designed a single neuromorphic neural network (NNN) that can learn, self organise and self categorise information. The NNN can learn to recognise objects/ words given ocular input, or given time the same NNN can adapt through plasticity and learn phonemes/ spoken words (see vids) with no user input, totally unsupervised.  The same NNN handles long/ short term memory, prediction, episodic memories, etc.

I think the collection of artificial neurons, glial cells, etc, has the same ‘innate intelligence’ as the biological systems described earlier.  I believe that this simple low level ‘intelligence’ is what compounds to produce our ‘high (lol)’ human level of intelligence.

I have expanded this model to produce an artificial whole brain connectome seed based on the layout of the human connectome.  The idea is that over time as the system grows/ expands and experiences ‘reality’ I will learn more (always fun) and eventually figure this out and create a true AGI.

I know from experimentation that the visual cortex area can learn to recognise objects, and the audio cortex can learn phonemes, etc… now I’m letting other cortex areas learn their sparse outputs and feed back etc… just like I think the human equivalent does.

I’m basically drinking rum, reading AI/ neuroscience research/ white papers, figuring out how I think it all works, coding, running simulations and banging my head on the desk lol.

I think deep learning, heuristics, convolutional networks, etc are very narrow AI schemas and will never result in a true conscious, self aware AGI... I believe my approach will... my current connectome seed only has a few million components… but its growing… and it’s learning… and so am I.

 :)
7
General Project Discussion / Re: The last invention.
« Last post by Zero on December 17, 2017, 09:05:14 pm »
I understood everything you said, and your interpretation of what seems to happen with the second GTP makes sense, and sounds correct.

But I need to apologize for what I'm going to ask. I have to ask.
How do you know it's not just noise? The whole thing I mean, not only the second GTP. What intelligence does the whole connectome show?

It's a real question, I swear. Not an insult or  something. I'm a big fan of you and your Beowulf, just trying to follow and understand.
8
General AI Discussion / Re: Harmony, Complexity, and Chaos in a image
« Last post by ivan.moony on December 17, 2017, 05:20:38 pm »
Could values between 128 and 256 mean negative time, a time before the Universe existed?

I'm playing these days with complementary values. I find binary encoding of negative values fascinating.
9
General AI Discussion / Re: Harmony, Complexity, and Chaos in a image
« Last post by keghn on December 17, 2017, 05:00:18 pm »

 The Complexity Number

 Complexity number could be in a range of only 1 to 256.
 A value of 1 means fraction of a fraction of a second to figure out what its. And the most minimal a mount of cpu power.
 A value of 128 would mean beyond the life time of the universe. And great strain on cpu and gpu power. 

 Life and AGI need a fast way to deal with the easy stuff first, before wasting too much time on the too complex.

10
General Project Discussion / Re: The last invention.
« Last post by korrelan on December 17, 2017, 11:55:45 am »
Quote
What is GTP?

The global thought pattern (GTP) is a term I give to the whole brain-wide pattern of activity within my AGI’s connectome.

Memories, logic, intelligence are expressed in my AGI by the frequency differentials between separate groups of neurons.  Each area of the 3D connectome is a collection of cortical columns that learn to do disparate jobs within specific frequency bands.  This means that each neural ‘module’ can process the internal/ external sensory stream differently depending on what the AGI is ‘thinking’ about, the modulation of its neighbours effects what each module does with the information it’s given. 

During my research into episodic memory engrams I had noticed that a second GTP was emerging, it is basically piggy backing off the main GTP but is out of phase, and because it’s using the same neural architecture as the main GTP it influencing how it processes data… it’s very weird.

The new GTP is being driven by the harmonics of the main GTP.

This didn't’ arise until I started integrating non sensory areas of cortex, ie the frontal cortex. The frontal section basically learns the output patterns of the sensory areas. It then sends feedback to the sensory areas influencing how they process the incoming data streams.  The feedback eventually causes a blending between the regions, where each is governed/ affected by the other.  This is a precursor to imagination; the frontal cortex can influence the sensory areas to ‘imagine’ a false sensory input based purely on learned external concepts/ experiences.  The system also uses this feedback to recognise its own internal ‘thought’ processes, because everything it ‘thinks’ goes back through concepts its learned through experience.

It’s similar to hypnotism or deep meditation…cortical regions are learning the harmonics… I was expecting the system to do something like this, just not so soon.  The new secondary GTP is like… just the surface froth, reading between the lines, or the summation of interacting logical pattern recognition processes.

Perhaps consciousness seems so elusive because it is not an ‘intended’ product of the connectome directly recognising sensory patterns, consciousness is an extra layer. The interacting synaptic networks produce harmonics because each is using a specific frequency to communicate with its logical/ connected neighbours.  The harmonics/ interference patterns travel through the synaptic network just like normal internal/ sensory patterns.  Perhaps our sub-conscious is just out of phase, or to be more precise, our consciousness is out of phase with the ‘logical’ intelligence of our connectome.

It was very difficult to track the patterns within the GTP but now it’s even harder lol.

This could just be a unforeseen error/ design problem of course…I need more Rum.

 :)
Pages: [1] 2 3 ... 10

Users Online

36 Guests, 1 User

Most Online Today: 49. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)

Articles