• Announcements

    • khawk

      Download the Game Design and Indie Game Marketing Freebook   07/19/17

      GameDev.net and CRC Press have teamed up to bring a free ebook of content curated from top titles published by CRC Press. The freebook, Practices of Game Design & Indie Game Marketing, includes chapters from The Art of Game Design: A Book of Lenses, A Practical Guide to Indie Game Marketing, and An Architectural Approach to Level Design. The GameDev.net FreeBook is relevant to game designers, developers, and those interested in learning more about the challenges in game development. We know game development can be a tough discipline and business, so we picked several chapters from CRC Press titles that we thought would be of interest to you, the GameDev.net audience, in your journey to design, develop, and market your next game. The free ebook is available through CRC Press by clicking here. The Curated Books The Art of Game Design: A Book of Lenses, Second Edition, by Jesse Schell Presents 100+ sets of questions, or different lenses, for viewing a game’s design, encompassing diverse fields such as psychology, architecture, music, film, software engineering, theme park design, mathematics, anthropology, and more. Written by one of the world's top game designers, this book describes the deepest and most fundamental principles of game design, demonstrating how tactics used in board, card, and athletic games also work in video games. It provides practical instruction on creating world-class games that will be played again and again. View it here. A Practical Guide to Indie Game Marketing, by Joel Dreskin Marketing is an essential but too frequently overlooked or minimized component of the release plan for indie games. A Practical Guide to Indie Game Marketing provides you with the tools needed to build visibility and sell your indie games. With special focus on those developers with small budgets and limited staff and resources, this book is packed with tangible recommendations and techniques that you can put to use immediately. As a seasoned professional of the indie game arena, author Joel Dreskin gives you insight into practical, real-world experiences of marketing numerous successful games and also provides stories of the failures. View it here. An Architectural Approach to Level Design This is one of the first books to integrate architectural and spatial design theory with the field of level design. The book presents architectural techniques and theories for level designers to use in their own work. It connects architecture and level design in different ways that address the practical elements of how designers construct space and the experiential elements of how and why humans interact with this space. Throughout the text, readers learn skills for spatial layout, evoking emotion through gamespaces, and creating better levels through architectural theory. View it here. Learn more and download the ebook by clicking here. Did you know? GameDev.net and CRC Press also recently teamed up to bring GDNet+ Members up to a 20% discount on all CRC Press books. Learn more about this and other benefits here.

Archived

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

bogdanontanu

Neural net is the ONLY real AI...

44 posts in this topic

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...
0

Share this post


Link to post
Share on other sites
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?
0

Share this post


Link to post
Share on other sites
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





0

Share this post


Link to post
Share on other sites
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.
0

Share this post


Link to post
Share on other sites
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**
0

Share this post


Link to post
Share on other sites
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
0

Share this post


Link to post
Share on other sites
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


0

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.
0

Share this post


Link to post
Share on other sites
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
0

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.
0

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.
0

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.
0

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.
0

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

0

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.
0

Share this post


Link to post
Share on other sites
We already have AI, it''s used in games all the time.
If what you are talking about it real intelligence, then call it that! Call it "real intelligence". AI is merely the artificial simulation of intelligence, which can be a mere calculator, since it can give you intelligent answers to given problems.
It seems that after the Matrix, that single line about us "giving birth to AI" has made people think that the AI in games and such right now must not be "real" AI. When I first saw that movie, and that line was spoken, I thought to myself "what the hell are they talking about? We already have AI."
Don''t get me wrong, I love that movie. All I''m saying is that the term "AI" is being mis-used.
0

Share this post


Link to post
Share on other sites
Good point Cessan. I didn''t catch that in the movie. I was still trying to figure out why Morpheus hasn''t called me yet. I guess I better get a cellphone.
0

Share this post


Link to post
Share on other sites
I''ve read the whole thread, and I''d like to ask a few questions (not necessarily phrased as such, but they are) and make a few (possibly invalid) points:

First, why in the world would the earth represent the only kind of artificial intelligence possible? The entire evolutionary history of life on earth is based on a very small number of original forms. It''s not even necessarily true that DNA is the only encoding scheme for life itself, so the brain may or may not represent the only intelligence hierarchy. We''re subject to the environment, and most good ideas (ie neural nets et al.) still come from the natural world.

Second, there is the question of how accurately the human brain maps to a minimalist view of intelligence. It''s based on a set of layers developed over the course of evolution and it''s a really nice machine, but so are most SUVs. It''s just that power locks and power doors and their intellectual equivalents aren''t necessarily required in terms of pure function. On the other hand, the brain pulls some neat tricks outside the realm of chemical signals using a kind of structure called (I believe) a microtubule. The basic thing about this guy is that it brings quantum theory into view inside the brain. As anyone who''s studied NNs knows, the basic hierarchy of nets is essentially digital. Fuzzy nets may or may not get around that problem. But if we *could* design nets to be intelligent, they''d likely be a LOT smaller than the brain, probably orders of magnitude less expensive - which is still a lot of power, but it certainly helps!

Hmm. That moved away from games a bit too much, so let me justify: In the context of a game, it''s necessary to do one of two things - spend lots of time building a fast AI machine with grueling work every time or build one fast NN hierarchy once and then train it each time, spending lots of computer time in-game to make enemies "smart". But there''s no reason that a smart interpretation of output vectors can''t at least reduce the amount of work that has to be done - using, for example, a single hierarchy to simulate an entire class of soldiers, or even limiting NNs to COs, if you will, who then disseminate "smart" instructions to the dumber brute-force or traditional-AI forces. Not appropriate to all genres, certainly, but to enough to make things interesting, at least.

Last, but not least, there is the question of how well a NN captures the function of the brain. Fortunately, here there is a really good guideline in Creatures, which did a lot of neat stuff, particularly in the inclusion of "modifiers" which changed the effects of a variety of stuff in the net. Don''t remember the mag (New Scientist, maybe), but one of them had an interview with that dude what programmed it. Creatures, of course, had the luxury of CYCLES GALORE, but still. The brains there could learn to speak and eat and feel "scared" and all sorts of neat stuff. Recognizing "scared" as an output vector is a task for the designer: what should make a unit scared in the first place. Once that''s determined, the output is mapped. The class isn''t as clear as one might like, and multiple unique outputs might have to be considered equivalent, but the possibility does seem to exist.

Anyhoo, that''s my seven cents,
mikey
0

Share this post


Link to post
Share on other sites
A lot of very good young programmers have the habit of thinking in terms of ultimate simulation -- complex experimental applications of code to reproduce everything from the mechanical pysics of a muscle to the most minute reasoning of an artificial intelligence in it''s environment. This is similar to the writer whose every short story becomes War and Peace or the artist whose every sketch aspires to the Cistine Chapel.

This is something we, as creative talents, must learn to overcome in the interest of productivity. Think of it as optimization -- for a game the only concerns are those aspects which have some bearing upon the tasks and goals required to play. Or for pawns along the wayside, only the tasks and goals needed for them to achieve their purpose in the player''s experience. It is almost certain that leading computer games will never utilize perfect neural simulation as other areas will continually demand their own portion of the available space and processing power -- rendering ever more expansive and detailed worlds, endowing those worlds with ever more immersive aural depth, supporting broader and broader variety of inhabitants.

It is my firm belief that the ''virtual human'' will and should remain a denizen of the virtual laboratory, where the platform is always as powerful and specialized as it can be and the environment always geared to simulation without the restraint of game rules or performace.
0

Share this post


Link to post
Share on other sites
Now maybe i should start a new thread....because this gets hard to read from start to end....

Hmm...Anyway i''d like to make a synopsis one again:

1.I stated that NN are/or can be almost exact copy of our brain an more important they can evolve (is a certain level of hardware is given) like any Real Inteligent ppl from this board

2.Some ppl douted that emotions can be "understood" by NN
others douted they can even work

3.Some exaples provided by other ppl that replyed here show that they work very well and more i stated again methods to evolve and DREAM and be creative....now about emotions i have to agree with another reply post witch explais that emotions are just "pattern of behaveiour" and so any NN will do them if proper trained.

4. Ppl are still afraid of this ultimate understanding of our "robotics" hardware....well some will always be

5. Some real problems where raised:

5.a Is today hardware capable to do a minimal NN to be human like inteligent...and so generate our first human being?
My Answer: is YES we only neeed some millions neurons up to a billion to understand the whole UNIVERSE and our hardware is now capable to provide that at a resonable dimension.
Downfall: we still have problems with interconections between those neurons....wires are the most expensive part in an artificial brain as in our brain (myeline isolations take almost 90% of our brain...)

5.b can we train a NN to "instant" have same IQ as a humman?
Answer: Not yet as i know it....(military ppl may know better). Problem is that it really takes time to train any beeing to be intelligent ... but if u train it long enought it WILL....

5.c can we copy NN once trained?
Answer: yes this is very easy...just make the same config and preset levels of trigger same as those of "trained" NN...and ooops u have an identicaly person created...better than clones i am sure....

5.d Some ppl have complaints about complex chemicals involved in brain functions...that we cant reproduce/understand yet...
Answer: Well do you think u know all phisics in ur PC microProcessor? (i think you dont even know how it works beyond basics) but you see it only sends electrical signals from one gate to another.. u can replicate it chemicaly or mechanics if you so like (only to make it huge) but it will work the same because chemical subst and electrical signals are only support for information they are not of the esence here......

6.Some ppl pointed out ...as i did also ... that there is a little more improvements in our brain (like tunneling over speed of light mybe...and bypass connections) but i think this are also not of the essence....NN is the main ideea here...and if it works just fine to make a humman being i think we can let improvements for later...

7. Some ppl think that "simple connections" cant be inteligent....lol...matbe they dont know how theit brain works..let me explain it a little:


General NN operations /trainning
=================================

A NN i maked by multiple layers of simple neurons
there are at least 3 layers (but usually many more)

First layer takes inputs from outer world (like pixels from video cameras) data form microphone, sensors for tactile inputs etc

Second layer makes connections each input to each output of the first layer this is the actuall brain so there may be many may more layers here

Third layer takes inputs form second layer and sends output to action making organs like voice or movement or other execution chains

Now how the hell does it work?

Loke this
A. present imputs with relevant data: like a cat to the video camera (you should start with circles or rectangles but we dont have time for that)

B.signals from inputs wil "fire" if certain (even random) levels are meet.Secondear levels will also fire some signals and so will third level (observe that all "fiereing" sequence depends on "levels") so some actions ... stupid at the beginning like the hummman will cry or even make "pipi" am himself will happen...

C.You the "mature person" know that the NN should say "this is a cat"... and dont like "pee on himself" do you
so tell the (actually do smthing drastic like yell at that thing) NN that he had done wrong (maybe even have Right or Wrong button installed)

D. NN knows she/he did wrong... so downgrade all levels that fired early and upgrade other (maybe even random) links levels...so next time you will get another response...
do so until you will get the proper response...(it may tahe a while but it will...u can even help a little in the beginning )

now this help is easy to do if this is the only thing she knows (just push the good damn "cat" link... ) but if more things are inside you have to NOT destroy the other good answers from before training....
this generatea a system of equations .....that you can resolve...lol mathematicians try this way...
or you can just push up random levels but from those involved in early lernning...because all of our world has a linked logic in it dose it not?

Well if you follow until here and you are not loosed... then u get the big picture ... dont you...?

I is Simple....and its in your brain and a machine ca do it the same way.... we may or may not have the time to create such a beeing yet....but we understand now that it can be done....very soon if not allready...

Nice eh...
0

Share this post


Link to post
Share on other sites