Scratch

any kind of system you develop with Scratch will not be AI. Even the most advanced programmers with the best software in the world have only a hazy imitation of AI at the moment. anything you make with scratch will only be intelligent to the level you give it.conditions can be used to cause different behaviours, but you're not gonna get any AI.

unless you have the same maze every time, rather than a randomly designed one each time, the bot will actually almost always take long than a human to find the way out, even in a simple maze.

AmoebaMan wrote:

the fact is, Artificial intelligence is impossible to create.  doing so would be playing God, and you would probably get struck by lightning if you did succeed.  anyway, because computers are only capable of understanding two values (1 and 0) and two functions (add and bit-shift), it is impossible to create a program that could do what the human mind could do.

that being said, i think what you are looking for is a CBR (computer behavioral replicant).  those aren't that difficult to make.  you just have to make a @#$%-load of "if" statements to define every possible scenario.  either that or find a mathematical formula that could be used to define those if statements with given inputs.  or a combination.

it will be possible to mimic intelligence to such a level that it becomes indistinguishable from real intelligence in the future, but I don't see anything like that happening soon. I'm currently studying Robotics, so I know what I'm on about.

To be honest, the human mind can be seen as a load of "if statements" anyway, we use things called scripts to work out how to behave in different situations, e.g. your script at a football game and a library are very different. Humans use classical conditioning just like machines can, it's just the we have thousands and thousands of "If's" that are constantly being improved, revised and modified by new knowledge, something computers find harder.

you guys should look up "Turing Test"

ps. AmoebaMan ; nobody wants to know what your church, cult, faction, or regime has to say about playing god

G-factor = God.  Humans are much more complex than trillions of little "if"s.

And anyways, it probably would not be good to create a machine with intelligence parallel to that of a human mind.  If you have ever read "Footprints of God" or watched The Matrix, you probably know what I mean.

nXIII wrote:

AmoebaMan wrote:

G-factor = God.  Humans are much more complex than trillions of little "if"s.

And anyways, it probably would not be good to create a machine with intelligence parallel to that of a human mind.  If you have ever read "Footprints of God" or watched The Matrix, you probably know what I mean.

Um... what god? No they aren't....

i will ignore that blasphemous comment...heathen...

lol jk.  even if you don't share reasoning with that first statement, you might consider the second one...

<reset timer>

that being said how do you make a CBR

sparks wrote:

our entire consciounce revolves around trillions of if statements, that let us react according to everything we experiece, from having a bath to driving a car, we use past experience to do them, eg, during previous baths, the water has always been wet, generally stayed in the tub, and we are supposed to wash ourselves. We assume this will be the case with the bath we are having at the moment, even though there is nothing to say that those things will be the same this time. In a car, we assume the wheel will do exactly what it did every other time we used it. Our previous experiences reflect our current and future reactions.

when we come across something we have never seen before, we can use past experience to decide what best to do in the situation, this is the things machines find so hard, and give us an edge for the time being.

the fact is, on its most basic level, the brain is far more complex than the computer.  the signal system used to relay information in the human brain is far more complex than binary - thus, a computer simply isn't capable of doing some things that a brain can - namely, thinking entirely on its own.  a true artificial intelligence would be able to respond to events with no prior programming dictating those events, just like a human brain can.  an if statement can't do that.\

sparks wrote:

another example of learnt information is that things look smaller further away, which allows us to make sense of a two dimensional picture as having depth, even though it is all flat.

someone doesn't know their physics.  things far away appearing small isn't due to information modification by the brain - its basic physics.  as you get farther and farther away, the stream of light particles that actually reach your eyes gets smaller and smaller, which makes your perception of it decrease.

someone either needs to revise their physics or explian more clearly.

it's called perspective
Perspective, in the context of vision and visual perception, is the way in which objects appear to the eye based on their spatial attributes, or their dimensions and the position of the eye relative to the objects.

As objects become more distant, they appear smaller, because their angular diameter decreases. Your view on the world could be thought as an onion where each little layer represents a distance from the eye. As the distance gets larger, the surface area of that layer of onion becomes larger and larger. Because you see things in angles, the angle seen of an object would decrease because the object would take up a smaller amount of surface area at the larger distance. Subsequently, objects that are farther away would seem smaller. (I'm currently studying physics, robotics and psychology (and randomly German) at college)

Humans learn from early on that this is the case, and I was merely mentioning that things DO look small further away, and most people have cottoned on to that... I wasn't referring to HOW or WHY things look further away.

as it is, we have to learn that faraway things look smaller, even if we don't know we learnt it because most people don't have solid memories that reach past their short term memory to long term until they are about three years old. If we hadn't learnt that, I think we would not be able to make sense of the picture.

think about it, you use both your eyes to judge distance, (if you want to try that out, get a ball and toss it erratically from hand to hand, then do it with one eye closed and see which is easier) so that means if we didn't know things looked smaller further away, a picture would not look three dimensional because our eyes would focus only at the same distance away for the sheet because the sheet is two dimensional, it is the ability to notice the perspective in the picture that lets us see it in three dimensions.

p.s, although light does display a few characteristics of a partical, such as the release of photons from a metal in the ultra-violet part of the spectrum, light isn't a partical, it's a wave.

sparks wrote:

aaanyway, humans process analogue information, that's true, but we store it digitally, using synoptic nerve connections in our brain and electrical currents that pass between them. when a new thing is lernt, a new connection is made (it will only be temporary at first, that is called short term memory and lasts around 20 seconds) but can be strengthened by repitition or association, in which case the connection can last forever.

I geuss I would learn that in biology, not physics?

sparks wrote:

hmmmm... I don't know if biology would cover it, I never studied it in depth, I lernt that in psychology, though I imagine it would be covered in bio too

Im more interested in Quantum physics than how the brain works. So aslong as the AI in the games I make are good enough then im happy. I just want them to react, sometimes unpredictabily, but thats it basicaly.

sparks wrote:

well yes, that's all you really need for a game, there are only a few if statements required because there aren't that many scenarios that the character can be presented with.

Depends on the game, but yes.

AmoebaMan wrote:

nXIII wrote:

AmoebaMan wrote:

G-factor = God.  Humans are much more complex than trillions of little "if"s.

And anyways, it probably would not be good to create a machine with intelligence parallel to that of a human mind.  If you have ever read "Footprints of God" or watched The Matrix, you probably know what I mean.

Um... what god? No they aren't....

i will ignore that blasphemous comment...heathen...

lol jk.  even if you don't share reasoning with that first statement, you might consider the second one...

blasphem-? Are you kidding me?!
...

Um... I hate to be the one to tell you, but there is no G-Factor, this 'God' you are referring to does not exist, and you can call me all the names you want, but it won't change that... Saying you believe in God is exactly like saying you believe in Flying Purple Bunnies with time-traveling abilities which rule over the universe, just because nobody has proved this wrong.

What second statement?

AmoebaMan wrote:

the fact is, on its most basic level, the brain is far more complex than the computer.  the signal system used to relay information in the human brain is far more complex than binary - thus, a computer simply isn't capable of doing some things that a brain can - namely, thinking entirely on its own.  a true artificial intelligence would be able to respond to events with no prior programming dictating those events, just like a human brain can.  an if statement can't do that.\

Remarkably enough, the system of relaying information can be replicated very easily with computers: it's called serial connections. So, let's say we're stuck with 1 and 0, you are correct that far. So how do we get 42? We use a serial port! That means that we send multiple bits of information over one channel. For example, sending 42 in an eight-bit serial connection:

   0       0      1       0     1     0     1    0     →  output = 00101010
   ↑       ↑       ↑      ↑     ↑     ↑     ↑    ↑
128's   64's   32's   16's   8's   4's   2's   1's

Add it up and...tada! 42! We can now relay numbers up to 255 with our 8-bit serial connection, which sends the bits in order for very short times, like what a USB cable does. With a 64-bit serial (or parallel, which uses separate pins for each bit, so is naturally faster) channel, we can send numbers up to 18446744073709551615 ! Now can YOU do that? And think about it, by using immense parallel ports, we can send whole paragraphs of text at one time!

AmoebaMan wrote:

someone doesn't know their physics.  things far away appearing small isn't due to information modification by the brain - its basic physics.  as you get farther and farther away, the stream of light particles that actually reach your eyes gets smaller and smaller, which makes your perception of it decrease.

Um... someone needs to look this up or get their physics right. Let me Google it for you! (third result)