Jump to content
  • Advertisement

Archived

This topic is now archived and is closed to further replies.

bogdanontanu

Neural net is the ONLY real AI...

This topic is 6942 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

Recommended Posts

Yeah man, and if you put an infinite number of monkeys in a room with an infinite number of typewriters you''re gonna have a lot of shit to clean up and a Hell of a typewriter repair bill.

Face it, there''s no way we can simulate a human being with simple connection/node NN''s. We''re far more complex than that, we''re full of chemical complexity we don''t even understand yet, yet alone are able to simulate.
It''s gonna take a long, long time.

Mike

Share this post


Link to post
Share on other sites
Advertisement
There is ABSOLUTELY NO WAY that one day a computer will contain a simulation of our world!
Think about it! What is the world build on? Athoms! (Ok, it goes smaller than that, but that''s not the point)
How do we define an athom? Some coordinates perhaps? ok!
it has got speed! Put in some speed variables! How many Electrons (ME! =) are there circulating around the athom? what''s their position? a hunderd bytes more.
Fine! we''ll end up at an athom with the structure of 1k bytes, and that''s even when we are simplifying the whole thing!
Even the smallest hard drive cannot store a bit smaller than an athom! That''s the final limit.
Now, use some maths. If we wanna duplicate our own world, it will need a harddrive bigger (Physically) than the world times 1000!
Screw you Eniac, you''re like DUST compared to this hardware!


Electron

"Who need more than 640kb of RAM?" -Bill gates -89


Share this post


Link to post
Share on other sites
Heres something to keep this post going:

Suppose WE are all simply an extremely advanced program? Maybe we are designed the way we are beacause our creators had higly advanced technology? Maybe the reason it is so hard to trace evolution to its absolute root is because the original living organism was not, as we think, the first living organism? Maybe this organism was created by an advanced species, who themselves were only a creation of another species before them? One day our evolution may lead to a species capable of developing a similiar "living" technology, able to reproduce, repair and grow. Just think about it. BTW my response to anyone who wants to dispute me is this : Prove me wrong, and ill see you in 50,000,000,000 + years to congradulate you.

Share this post


Link to post
Share on other sites
Guest Anonymous Poster
bogdanontanu: I have a question for you. How would you train a neural network to be scared? I''d like to know. I''ve been studying neural nets as of late, I even bought a few books on the subject, but not one of them even attempted to claim any of the things you have. I''m not trying to attack you, I''m just trying to point out that we, as humans, dont even fully understand why we feel fear, or what triggers it. Fear is not simply a learned response, it occurs instinctually and is accompanied by a chemical cascade in our nervous system/brain. I''m bet cash money that it would be extremely difficult to model even the behavior of a cat, or mouse. There is so much more to simulating thought than simply simulating neuron interaction. Especially when you have a brain stem(which can bypass your brain altogether for reflex actions), emotions(which often are accompanied by neurochemical cascades), and instincts that act as catalyst for complex thoughts.

I really would like to see you teach a neural net to be scared...

--Cauldron the Evil

Share this post


Link to post
Share on other sites
Why don''t we take a brain a hook it up to an computer interface and use it from there?

My roommate was talking to me about where the "soul" is? It seems to be located in the brain. You can have artifical hearts and limbs... etc. But there''s no artifical brain yet.

Share this post


Link to post
Share on other sites
To Anonymous Poster.

You talk of ''scareness'' as if it was a concrete entity.
Scareness and other types of BEHAVIOURS, are just behaviours.
Behaviour is a pattern experienced by an observer. The pattern is caused by an active object. For instance, a plant is observed as a plant, but it only contains chemicals and cells which operate together and their "behaviour" causes the object to be experienced as a plant in an observers mind.

Therefore I think you can''t train a network to be scared, as it''s a behaviour CAUSED by a neural network. But you might surely train a network to ACT scared. But the nn must live in some kind of world. You won''t get a "scared"-vector as output. I mean, a (0.2 0.234 0.75)-output vector can never be defined as a "scared"-output. But the output might start an active ''scared''-behaviour.

That''s my view, but it might be upside down

/Mankind gave birth to God.

Share this post


Link to post
Share on other sites
You guys need to understand, that chemicals (emotions) influence the flow or the neural net. In this light, a human can''t be truely emulated by hardware. BUT, using our abilities of abstraction and math, we can simulate these emotions just as we can simulate our brain''s neurons.

Here''s the one problem : input. Our brain has only one output : behavior. That''s the sum of all of our current input and internal stuff. We can simulate the internals with math and our current technology (to some extent) but the world we live in is infinitly more complex. It can be simulated, but with our life span, I doubt we will ever do it.

Also, you can''t logically prove that something can''t be done. Think about it.

Share this post


Link to post
Share on other sites
to wanderer

If you commented my "can''t".
Of course I don''t mean that you can''t train it to be scared. Don''t take it literally. What I mean is that you train the net to BEHAVE scared.

Life is an illusion.

/Mankind gave birth to God.

Share this post


Link to post
Share on other sites
Actually I think evolution gave birth to God but that''s just me being pedantic =)

I think there''s a couple of main points here.

Firstly, it is very difficult to hand generate a neural net bigger than a few neurons for more than a very simple task. You either have to specifically create it with from finite state rules, which is really pointless, or work out all the maths before hand which is a long and laborious process and impossible for large neural nets.

The best method of creating large scale neural networks is evolution and genetic algorithms.

The second point is, how do you evolve a human being?

The easy answer (and it isn''t easy) is to make the fitness function ''likeness to a human being'' or the artificial environment like our own in which a human being is the best fit answer (or at least we think a human being is the best fit answer).
Remember though that our environment wasn''t initially like it is today and our 3 billion years worth of ancestors didn''t evolve in this world. We are also one of at least 10^1000000000 solutions to the problem of survival on this planet and we are undoubtedly not the best. We are just the best that has managed to survive and evolve, which makes us lucky more than anything else.

What I''m trying to say here is that any form of programming, be it AI, specifically NN or Genetic Algorithms or any other type, is a solution to a problem. What is the problem you''re trying to solve? Why is simulating human beings a good problem? Why solve what''s already been solved in nature?

In artificial envoronments you may well evolve simple creatures that react to certain stimuli with emotions or with something simmilar enough to pique your interest. Emotions are obviously good for survival else we wouldn''t have them. But there''s only so far you want to push the human analogy.
As I said, pick a problem and solve it, just make it more interesting than the simulated human one.

Mike

Share this post


Link to post
Share on other sites
The number or neurons is the biggest thing. We have 10^11 number of neurons in our brain. A 100 simulated neurons is not enough for a game AI. A typical worm has 302.

Share this post


Link to post
Share on other sites

  • Advertisement
×

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

GameDev.net is your game development community. Create an account for your GameDev Portfolio and participate in the largest developer community in the games industry.

Sign me up!