AP raises interesting points. Apparently i am diverging from the original post so i'll make this one short.
About sleep: yeah, i believe the same, specially considering the reports of people getting confused after a few days awake, even if properly fed and rested. On a statistical model sleep = token compression = find abstraction and equivalences,eliminate low-usage tokens, renormalize probablilities(depends on how you store them). This also means that the process needs some time to complete, and if interrupted the bot would be quite confused, just like we are when woken up on insufficient sleep.
About reading our own machine code: funny and insightful. yes, we can't read our code and thus we cannot (directly) generate new one. And if we could, we'd screw up an die as you said. The way to consciously modify one's own behaviors is by observing their effect, and then using the prediction model to find a new behavior with the desired effect.
What does that mean? that for the bot to be self coscious it has to be able to perceive itself, and perceive others as similar to itself.
In a chatbot, you would feed what the chatbot says to its own knowledge model along with a personal ID (nickname|IP for IRC).
woop, made it short. Agreed with jtrask, this thread seems to have no goal, but neither did I. And already got something interesting out of it, so yay!
Creating A Conscious entity
Careful now. Glad to see that you're getting focus, but be wary of drawing biological parallels to a non-biologically-inspired system. Why do these things need sleep? Can't it do these things in the background? True that we can't edit our code, but then again, our code is not the same as the code you would use for such a system. Our neural code isn't exactly editable, but at a local low-level it is changed. That's what learning is. Since you're not coding a neural net, it's not entirely applicable. But why not allow it complete access to its own code? Or at least within reason? No need to make circular connections that are harder for it to learn when you can just feed it in directly?
i guess you could do it in the background, but i think its a rather expensive process so even if throttled there are some big atomic operations that cannot be interrupted... but hey, maybe it could be done with the extra paralelization work.
For allowing it to mutate it's own code, you'd need to make it interpreted code, and thats more work. If it's already interpreted then it should be interesting to try. Each script language could be a token, too.
For allowing it to mutate it's own code, you'd need to make it interpreted code, and thats more work. If it's already interpreted then it should be interesting to try. Each script language could be a token, too.
Author
Yeah, this thread has no exect goal.
I was thinking of making a cross between a nice-sounding bot, and an intelligent bot. So that it would be rather nice to talk to, and could "understand" some consepts, as well. (along with what if questions, and the usual why, where, when, ect.)
With generalisation,
How about this:
for each node, counter x
For each other node, counter y
If the quotiont of the links (amounts different, if one has a link and the other doesn't, its treated as a link with the amo of 0.00), abs(x,y) , is smaller then some smallish constant, then:
Grab some random links, that x doesn't have (or that x has, but with different amounts).
Integrate X, and Y. (includes averaging link amo's, to find the new one, in the case of two links which are linking the same two nodes together).
Remove y
next node
next node
now, with this, it would start doing some generalizing, in the heigher order nodes (i would say, that the nodes for heigher order consepts tend to have a mass of links, but lower order conspets tend to have similar, small amounts of links).
??
For the what-if questions,
How about temperary nodes/links/rules?
If you uwere a bird, and could fly, what would you do?
Well, you would make a temp link, from self to bird, and (if not already there), make a temp link from bird to fly.
what would you do, signifies an action, that the thing "you" would perform. so, the bot should look up bird's links to actions, and figure out that birds eat, sleep, and fly.
It would then respond: I would eat, sleep and fly.
The temp links, ect. Would then be destroyed at the end of the session/ when it is no longer usefull (hasn't been talked about for a while)
From,
Nice coder
I was thinking of making a cross between a nice-sounding bot, and an intelligent bot. So that it would be rather nice to talk to, and could "understand" some consepts, as well. (along with what if questions, and the usual why, where, when, ect.)
With generalisation,
How about this:
for each node, counter x
For each other node, counter y
If the quotiont of the links (amounts different, if one has a link and the other doesn't, its treated as a link with the amo of 0.00), abs(x,y) , is smaller then some smallish constant, then:
Grab some random links, that x doesn't have (or that x has, but with different amounts).
Integrate X, and Y. (includes averaging link amo's, to find the new one, in the case of two links which are linking the same two nodes together).
Remove y
next node
next node
now, with this, it would start doing some generalizing, in the heigher order nodes (i would say, that the nodes for heigher order consepts tend to have a mass of links, but lower order conspets tend to have similar, small amounts of links).
??
For the what-if questions,
How about temperary nodes/links/rules?
If you uwere a bird, and could fly, what would you do?
Well, you would make a temp link, from self to bird, and (if not already there), make a temp link from bird to fly.
what would you do, signifies an action, that the thing "you" would perform. so, the bot should look up bird's links to actions, and figure out that birds eat, sleep, and fly.
It would then respond: I would eat, sleep and fly.
The temp links, ect. Would then be destroyed at the end of the session/ when it is no longer usefull (hasn't been talked about for a while)
From,
Nice coder
Author
I was wondering, how much processing power would this require to run?
How well does the algorithm fare?
What optimisations on it could be performed?
From,
Nice coder
How well does the algorithm fare?
What optimisations on it could be performed?
From,
Nice coder
A problem I see with this idea, is that do any human languages, computer or not, have the capactiy to describe how the human brain works? I don't think we can solve this with conventional languages. A cross-referencing node could work, but think of the network you would need. An answer to the question 'how are you?' can't be pre-programmed. The AI would need to know its current 'state', it would have to be able to do a self-diagnostic, and form its own answer, and cross-referencing would only produce what is inputted into it. It's almost like using a dictionary. The dictionary contains knowledge, but does it learn? Does it know the meaning of the words? Can it explain the words differently? How ironic is it that we, with our inferior vocabilary, require the use of such texts, which are utterly stale, to gain knowledge? The only possible way I could see to create an AI that is more than the sum of a datatbase, would be to copy the human brain. Has anyone read the book 'halo: the fall of reach' by Eric Nyland? The description of how they created 'smart' AI's could sort of be a solution. Its almost like programming in a way: you don't have to understand the code to use it (<--- this isn't the smartest way to do things, but if you're on a tight shedule, well then...) Anyway, again this brings me back to our language problem. How do we convert a human-type conciousness into electrical pulses of 'on' and 'off'.
Go for it but I doubt we'll be able to do this for another 50 years (according to a law that says processer power doubles every decade, computers and AI should overtake humans by then - The Matrix, anyone?)
Go for it but I doubt we'll be able to do this for another 50 years (according to a law that says processer power doubles every decade, computers and AI should overtake humans by then - The Matrix, anyone?)
Quote:Original post by Anonymous Poster
(according to a law that says processer power doubles every decade, computers and AI should overtake humans by then - The Matrix, anyone?)
I believe that the rule was that processing power doubles every 18 months. It's called Moore's Law.
Now actually about the topic, I was wondering if you guys think it would be possible to make a computer conscious not by manipulating 'inteligence', but emulating the physics of the brain down to the smallest particle. I know that this isn't possible now, but theoretically, would the emulated brain be just as conscious as the person's brain it was emulating?
If we could make a computer "exactly" emulate every smallest particle of a human brain then YES, it would be just as concious, and could at that point ALMOST be classified as a 'living' object. Kind of a scary thought actually, a computer every bit as aware and intelligent as a human but can process ideas millions of times faster thus growing its intelligence all the much faster...maybe we would no longer be the dominate species...dum...dum...dum...*erie music*
sorry I was in error about Moore's law. I wrote the response off the top of my head. In theory, in sheer processing power, computers can over take us. I think using a complex (more complex, than as I said, current languages can describe) or several complex algorithms to develop inter-connections between data. This could be described as 'thinking', as we develop knowledge by building connections between things we know. This is what I personally believe would be the most feasible course.
This topic is closed to new replies.
Advertisement
Popular Topics
Advertisement
