Tuesday, December 23, 2008

My challenge

Today I challenged myself to translate what I'm thinking into some robotic logic as I went along my day. I am starting my slate clean in my head to try to come up with better ideas. So now for what I have learned.

There are a lot of complex patterns I have learned. Muscle control is a funny thing, specific muscles used to do certain things, that I didn't notice before. When observing things, I found that those things I found funny were those things that were ironic and don't really happen. Thought processes are intricate and seem to be triggered by things I have noticed before in the past.

So I have concluded that observing is a key in a human mind, not only observing but when given a similar scenario, one needs to know how to apply it...learning to observe?that's going to be tough, it's an instinct i dont know how we do it.

Monday, December 22, 2008

Jumping right into my thoughts - may be difficult to read

currently the processes we have are only given under very limited circumstances, they are specifically made to learn different tasks. We could continue looking at differenet tasks and trying to replicate them until we get something right, or we could try something else.

When we talk as I have discused earlier we see more than just patterns of a subject and a verb and such. Things mean things to us differently depending on context of situation and many other things. Well, there's even more that we understand that computers don't. Computers don't know how to take commands and actually well... do them. If I say to a computer "make a pong program in java" it won't, even the software we have now will not. Maybe once a computer can understand what we say, it will be able to do what we do.

Now onto another thing that crosses my mind:

mutating pattern makers. 
What if we could find a way to mutate code and then select the best mutations given a selection pressure. What about learning techniques. 

what if we had a learning algorithm that tought a computer to learn to make learning algorithms instead of everything we're doing now. So if we could just give this learning algorithm the goal, it would write a learning algorithm to do it. 


WHY DID I DO THIS?
well, this is stuck in my head and i had to get it out. I'm hoping my creative juices will come up with more. I realize some is repeat, a lot of it is just additional stuff here and there as continuation of other thoughts, I get stuck on a thought to long and I need to get creative.

Sunday, December 21, 2008

Comments on Research / where to look next?

I am more or less paranoid that someone will read this and think I'm taking myself seriously in such a way that I firmly believe everything I type here. So I need to mention somewhere that I know I'm not a big shot (yet... maybe????I'll sure try), and I am simply brainstorming. 

Without further to do... the real reason I write this.

Alright so far machine learning is a couple different types of learning. supervised, unsupervised, ones where they give the right answer and one one that wont. To me this leaves a lot less than I want. Don't get me wrong I love it and i'm currently making a second tic tac toe program,my first one was perfect but looked at all possible outcomes, that will learn everything by playing against itself over and over again. 

Anyway, the problem with all of this is that the program only knows how to play within a very very very small context. So my tic-tac-toe over millions of games will learn to be perfect at it. Guess what, it's still just doing statistics sort of thing to figure it out. if I say "hi" it will do nothing at all. My question is, is all we are as humans really just a bunch of statisti crunchers, and if we are, by god we must have a lot of algorithms. 

Well ok the programs do learn better with 'experience'. My program will take millions of games probably to be perfect at the game. I only need maybe 100. Heck if I were really thinking about it I could have mastered tic-tac-toe the first time I played it, if I weren't 4. There's something missing, I feel like it's close but not there, not quite. 

I believe maybe if we both observe our own behaviors, maybe we can teach our computers to observe them and try to mimic. not only mimic but make smart variations within a context. Easier said than done, as usual.

Saturday, December 20, 2008

Ok... I lost control... I did moderate research.

I have decided I shall not wait in the dark and try to stab at this, I will branch off and read stuff. I recently watched a speech given by Kwabena Boahen from Stanford University about making a computer that works like the brain, and it involved neural networking. I have also watched a machine learning lecture on youtube from Stanford. And since this is a blog about me making ideas for myself, I shall leave that at that and start branching off the way my brain wants to.  

I find it funny how neurons in my brain are desperately all trying to figure out how neurons in my brain could be translated to a program, seems ironic.

Suppose we couldnt replicate exactly how our brain works using the appropriot hardware. We could still use software to do i, however it would be slow, as it would be using computer storing techniques to use a brain storing technique. So we need connections in the brain to be made in infinite dimensions! well, what I mean by that is the brain needs to sort the information with a lot of details, and be able to look for similarities with other information, and link those neurons to find patterns. My previous idea of 1,0, and both 1 and 0 seems almost silly now, as when I watched the program on neurons, apparently our brain uses 1's and 0's the exact same way computers do, just a heck of a lot more fast.

I really don't think computing power should be considered a large issue, I dont care how fast a virtual human can run, as long as it can learn the way you and i do, with the same positive features a computer has to add, such as a lot of memory and the ability to instantly memorize something.  We have a lot of storage space, more than humans can hold I bet. 


Yikes I forgot 2 entries today I guess.

Ok for the first entry I shall actually expand on the previous one, as I believe there is something else important in dimensions of logic. This time I am not so much thinking of dimensions of logic more or less I will talk about dimensions of intelligence. 

I know of sombody- not as a friend -at my highschool who does all the bad things, he makes a lot of bad choices. However, he is brilliant in AP classes, passes them without studying once. I origionally thought one with a lot of intelligence would make the right choices because it's logical, however there seems to be another side to it. 

My idea here is, should we be exploring how this difference works. If we need a computer to make choices like we do, apparently, well at my first glance it involves somehow more than logic -  sounds like it could be a title of a book.. maybe I'll write it. 

Thursday, December 18, 2008

Well... Oops? poor logic...

ok well in the previous I mentioned a thing about another dimension of logic, well I think I was wrong, but I am trying to stay one day ahead in these so that if I have a slow day I have a backup ready to go, and what I thought of for my next one nearly cancels this thought, but again I shouldnt ignore this one, as it may have life I am unaware, being a no0b and all.

So with a bit less passion, here goes:

What if there were something in logic we don't quite get. Some kind of emotion variable that makes us different. Well not just emotion variable but emotional logic. It is true that the brain has competition between these sides, are they two different types of logic. I think they would be, a 1 a 0 and a both 1 and 0. That would completely change the way programming is done.

There is also the possibility that all it is in emotion vs intelliect is simply more primal logic vs privious experience and what one has learned.


Tomorrow - nodes and networking them

Wednesday, December 17, 2008

Fractle Thinking

I got an idea in my head that at first startled me. For a brief moment I felt what i think someone else would feel when they make a new discovery that nobody else knows about. This was however short lived (though still, the feeling was worth it) as I soon realized it seems as difficult as everything else I have mentioned.

I was pondering how it is that we learned for a brief moment, especially how we learn things that computers can do better like storing information. It immediately occurred to me that we use repetition as a way of pounding information, each time we add a little more, make it more fine, until we get it. Suddenly it came upon me, fractals seemed to be the answer. As a lot of scientists know, we humans are made of many self similar shapes called fractals. With each iteration the picture becomes more complete, starts looking pretty nice. I started to think that maybe, just maybe that's how we learn, and how we could teach computers to do it.

I wonder if we could prove it like people have proved that fractals are the answer to receiving more frequencies, but i have no idea how that proof worked out and this isn't exactly a physics problem.

I always feel like I want to write about more than one thing in each, but my goal is to have 1 thing every day to talk about that's different. So as a self reminder, I shall say my next one will be about my pondering that 1's and 0's may not be able to do it alone, and that there may be another dimension of logic.

Tuesday, December 16, 2008

Genetics and Code

As I currently understand, we can map out our genome, and have found a few certain phenotypes from the genome. What if we could understand the process the body goes through reading the DNA. I imagine we could plug our own genomes into a computer and have a human simulator then. Then it would just be a long complicated process of trying to get the virtual human to use the computer's memory, and we have a human with infinite memory, then that human may become smart enough to improve him/herself to a point where the computer is capable of everything.

On the otherhand, why wait for us to understand our own. Maybe we could find a way to make something similar to DNA (1's and 0's?) and have those mutate and become selected with pressure until we get something smarter. Or what if we just had sooo much computing power, we could look at all possible binary combinations and a computer could recognize something intelligence (yes I realize what I just said was WAAAAY out there, again brain storming). not necessarily all combinations but all possible single mutations?

If only we could create some kind of behavior code. We as humans dont have a pre-set response for something necessarily, well in a lot of cases we do, but they're all behavioral quirks, it's all thses things that make us who we are, but how much of us do we need? I have the main goal of getting a computer to learn, I dont like the idea of giving the computer a preset understanding of what language is, a verb a noun and a subject. I dont know about the rest of the world, but when i remember speaking english and learning more, that was the last thing I thought about, and it definately wasnt pre set. I want to give a computer the functions to be able to come up with language the way we do, I think that is the only way we will ever get something that matches up with us in converstaional ability.

Monday, December 15, 2008

Thought for the day

As a side note, for my own insecurities, I must mention that i am simply brainstorming ideas, not necessarily to be taken seriously or as fact, now onto my thoughts

I still have some catching up to do on my ideas, but I would also like to mention that I am currently being ignorant to the way they do AI and Machine learning as of now on purpose, so I can make ideas on a clean slate before I am told what machine learning is, that way I could possibly use this to add to what is out there, before I am blinded.

Done with side notes:

Where is the line between how gullible you are, and how well you can pick up patterns. Suppose there is a very high reward for something and you don't know how to get to it, but you try the only thing you know 2 or even 3 times, how do you know the first time wasn't a fluke? what if it would have worked the 4th time? At what point would it be considered stupidity?

Or when it comes to believing something you hear or read, how would a computer be able to interpret what is true from false, it has to be a little gullible, but it cant have flaws in logic, or should it? CleverBot.com i noticed picks up language from its users, and from what i've infered it assumes that whatever we say in the context is what should be said, but this is not always true, but the computer always believes it. How would a filter on that work.

This is why I dont like what I hear about current AI, they don't seem to learn from scratch, they know one pattern and try to work with it, or just copy it, but it never bends it. Maybe a computer needs to learn how to ask questions, and benfit from it. So it knows how something can be bent.

I would write more but it's bedtime

Sunday, December 14, 2008

How it can be done

I'm no genius and I'm not going to say what I'm about to say is necessarily original, I'm sure somebody else has thought of this, nor do I say it is easy.

We are approaching the days where we can explain the physics around us pretty well, not perfect but we are getting there. If we were to get good enough that we could make an environment virtually, that would react the same or near same, we could replicate the evolution of this planet. Given we did that (not simple) we could end up with things as intelligent as we are, then take their code and modify it (again not easy) we could make our own super smart computer/person.

Of course for the current time that is not acceptable, to replicate the physics of an entire world would be very hard and require a lot of processing power, i believe more than we have, considering each and every single proton would need to be workiing the way it really does.

So maybe there is some sort of alternative? some evolving program that is not as complicated to start out. set the program to have being who have limits and their ultimate goal is to survive and reproduce, or simply have an algorithm to pick the 'best' solution and continue evolutions until the ultimate problem is solved.

Using this method could mean that something could be created that we might not be able to make ourselves if we turn out not to be smart enough as a species to do it the intellectual way. However, we could still combine methods so that we dont have to wait for the Higg's boson (if it truly does turn out to exist), and other discoveries, and the computer technology to take care of the computing power. So I would think the logical plan would be trying to mix these methods one way or another to get a result that works effectively. That's my current goal.

Saturday, December 13, 2008

Some thoughts and catching up

I recently thought of something peculiar that I wanted to add to my journal. A computer does the same task over and over again the exact same way, but humans would find doing something the exact same way over and over again harder, just as computers to get variation, we've come up with math and a time in order to create a "random" number and use that, adding additional tasks to get a computer to do something slightly different.

However I have been thinking about this stuff for at least a couple months, and just started a blog yesterday, so I have some catching up to do.

I have thought originally that a computer should have a basic goal to make it feel "happy" in order to get it to do tasks. We humans will look at a tree see it's there and maybe climb it, or cut it down to make shelter, or any array of things we can come up with because it allows us to survive or simply get 'happy'. Computers could understand-- understanding is a bad word, I'll get to that later-- everything about a tree and leave it at that, it's just there, even if it knows how to make all the stuff we do, it's incapable of thought in regards to why it would ever do that or get any sort of meaning.

This brings me to my thought on what understanding is. A computer records information very, very well. It can process things that would take an entire population of people to do, right at your fingertips. However, it can't do what I am doing right now, express something through fluent language. It cannot come up with thoughts outside regurgitated text, we as individuals are infinitely better than that than any piece of technology. To me at this moment, an important question is, "what is meaning?". I know what the word 'cat' means, but not by a simple text definition, and I can infer if somebody means something different than a physical cat by context - rather everybody can - but all a computer sees is C next to an A next to a T, and maybe stored bits of information.

What is meaning?
Is it complex patterns?
Can we as humans come up with this algorithm for meaning?
Do emotions matter when making something that can learn?

I have much more thinking i have done I need to write down -- including a sure way to get there but not necessarily safe, or necessarily efficient, but a simple thought that I promise would work if it were possible to make.

Friday, December 12, 2008

Introduction

I am currently a senior at my local high school, who has a big interest in artificial intelligence, and more accurately, Machine learning. I intend to use this blog as a way of journaling my own thoughts, but anyone is welcome to follow along and, if you feel so kind, point me in the right direction.

As of now my dream is to spend the rest of my life studying this, and I have a lot of ideas, whether they've been thought of already or not, I'd like to try some time in the future.

Feel free to read on.