Neural net is the ONLY real AI...

Started by
43 comments, last by bogdanontanu 23 years, 11 months ago
MikeD, what about emotions? We are all born with them, so they must be hardcoded into our genes. Yet how can you tell a computer to BE scared, or happy? Neural nets may be the best way for computers to learn, but learning doesn''t = life.
- Houdini
Advertisement
Well, i haven't read ALL the replies on this post, but as far as i can see, i agree about NN.
To make a NN grow free from scratch would take many many many many years of uptime.

BUT, let me give you some headache. If we won't let the program solve the evoultion thing itself, then who's gonna do it?
Do you REALLY want to set up a unique structure of billions of emulated cells? Well, i see you next millenium and see how it goes!

Don't try to cheat nature, don't try to outsmart nature, try to copy nature.

Electron



Edited by - Electron on May 8, 2000 4:36:41 PM
--Electron"The truth can be changed simply by the way you accept it.""'General failure trying to read from file' - who is General Failure, and why is he reading my file??"
We have no true definition of life. We cannot say what constitutes life or that a computer could never life up to our definitions.
Life, essentially, is a persistant chemical reaction, nothing more. Simulate chemistry exactly and you could do the same inside a computer. I don''t think that would make it any less alive than we are.

Also, emotions are just another form of stimulus, a mind set bought on by a given situation. They are quite easy to simulate but they make up a large portion of what seperates us from from a machine. So it is a large part of what you consider life.

Mike


Perhaps it would be easier to define what is alive, by defining what is not alive? or intelligent.

There are some materials that have shape memory. Is that alive? Intelligent?

Are rocks intelligent? They sure "know" how to follow the laws of gravity when one falls on my head. Probably too many have fallen on my head.

Nick
"If you build it, it will crash."
Does a machine have to do things the same way a human does to be intelligent?

Can''t a machine that achieves the same goals using different methods also be intelligent?

Check out my shadows page
and send me some feedback
Check out my shadows page and send me some feedback
Hey
belive it or not....all we are is only a neural net...

maybe ..only maybe (but its not req)there is a soul behind that neural net...but for now .. we just dont know..so we have to assume that ALL inteligence with emotions and with cretive actions is only NN doing...

And i have arguments for that:
1. A neural net (of course after proper training witch can take long time) can do everything a man can do.

1.a.it can easy do emotions you only have to learn it to
(hate/love for example) and i dont think more taht basic emotions are hardcoded into hummans
1.b it can DREAM... and actually it HAS TO DREAM TO IMPROVE without external trainning
What it happenes when a NN dreams? well you connect all his outputs to his imputs (also disconect outside world inputs) so it generates its own world of dreams ....
and this helps recognize paterns from events that take place early this day..also eliminates some random data...

1.c Cretive it will be.... (because starange things will happem in dreams...and tomorow it will try to take actions on that...and i may be right ar it may be wrong...but if its right,,,,wea..here we have a creator...
After all creators are just ppl with better understanding of patterns in this universe....an other ppl witch dont understand the world so well say it ia an ARTIST...hmm how may times where you considered almost a GOD by individuals that didnt know nothing about computers....see what i mean....

2. they have the power of Universe...

Do you know how many connections can be made form 1 thousand neurons each other to echother...
hummans have only some milions neurons....any haddrive has more now... but the neurons can be connected in more ways "than atoms in the whole universe"....

More to come if u are interested...

NN are nor so much known because of special military intrests in them...take care... and also because this is the first place where mathematics fails us...and sientists dont like it....there is no valid theory to explain how the hell do they work...but you see they do...

there are also some improvements in real humman brain NN but they are not of the essence (not very sure )
mainly they can have extra connections "on the way" ...
we can implement taht but for now we didnt understand simple connections....so this looks left for the future

they are also having some tunneling effect to speed up operations ... and go over the speed of light...some enthusiasts think...but nothing sure here... (maybe here is the soul ? hmmmm we all hope)

Ppl disagree with NN because for the first time we understand that WE ARE JUST SOME ROBOTS with all of our love/hate and creative thinking....and even the simple fact of giveing this a chance raises great fear....

Regards...
obysoft
here''s a thought:

it is pretty obvious that one day we''ll have an artifical universe simulation at least 99% accurate. Perhaps it won''t bother with sub atomic particles or maybe it will, whatever. So life is going to evolve in these simulations. If the simulations are run long enough the people in them will make their own sims, the people in them will make their own sims and so forth, eventually after so many layers the laws of physics will be so watered down that the creatures in those sims won''t get smart enough to make their own sims, still there will probably be millions of nested realities at least. Now here''s the question: what are the chances that we''re on top? Next to zero. We are almost certainly in an artificial world. Sure it''s real to us, but to the user on the outside we''re just a research project or a screen saver. Hmm maybe the theory or relativity just explains the implementation of floating point numbers on the computer our universe is being run on. Why not?
oi, that post made me flash back to college, sitting in philosphy 1.0.1 AND all the times I tripped out and smoked weed.

I suggest the basics Go read plato, aristophanes, aristotle, et. al. Who am I? Why am I? Where am I going...

I thought this topic was nueral nets





Just to jump on the philosophy thing briefly...

If we can simulate life on a computer, showing evolution, and can claim this ''life'' is as good as the real thing, then we have also shown that evolution does not necessarily have to exist and can believe in a creationist theory. And if we can believe in Creation, the whole simulation is not necessarily meaningful in the first place. Would we be simulating what we are, or what we think we are? Or would we actually be the simulation? Aaaahhh...

Somebody post some more pathfinding stuff. At least that makes sense.
Another little philosophy thing, that basically explains my take on what Bogdanwhateverthehellhisnameis has written:

If I have my ten-giga-terabyte *10E104 harddrive, and randomly assemble bits on it in every possible combination, chances are, one of them will be god.

That''s basically what you are saying.


#pragma DWIM // Do What I Mean!
~ Mad Keith ~
**I use Software Mode**
It's only funny 'till someone gets hurt.And then it's just hilarious.Unless it's you.

This topic is closed to new replies.

Advertisement