Somebody discouraged me, but I am back with a vengence

It has been three months since my last post. Since then I have slowed down due to college. I need to keep up with this blog for my sake!!

So in three months what progress has been made??

My idea (as i've researched and found out) is a more complicated neural network. This does not necessarily mean it will be more effective, though that would be pretty sweet.

So here's what's going on
The input will always be a list of numbers representing the environment to the algorithm.
2,3,4123,12,4,7.....
The Network, using its prewritten rules logic, will take the information bend it, twist it, multiply some stuff and get a result

The result will always be one number such as:
92

The environment will be programmed to use numbers in a certain way, preferably in a way that would be easy for the algorithm to adapt to later on.

NOW what's REALLY important is how we get from an array of numbers, to a single digit.

There is a huge map of 'neurons', these 'neurons' take in a certain amount of input, multiple numbers or maybe only one number, they do some logic and add some numbers in some almost random way (it changes over time, that's how i can find the best one), and then outputs ONE number.

Many of these things are connected to one another, the output from one neuron can be used by any other neuron that wants to know the variable, then spits out one number.

In the end, there is one deciding neuron that gives out the final output.

Many of these structures compete with each other to play a game. If they win more than others, they get to have babies, who are exactly like the parents, but with a few mutations. Then all the children and all the parents fight in the game, the best are selected, and the whole process moves over and over again.

Tomorrow: weaknesses, and how to make this better

Proof 2: Genetic algorithms, selection and fitness

Before I continue, I would like to define genetic algorithms to everybody just one more time...

Genetic algorithms try to replicated darwin's theory of evolution. problem is, we havent exactly evolved a human out of a computer yet... I wanna do that

Fitness: how well an organism does in its environment


I am trying to prove something... not quite sure yet, but this will probably happen a lot so I will be posting my previous remarks with this link. So if some number shows up, they should show up somewhere in these blogs below
Link to other proof post:
http://freelanmachinelearning.blogspot.com/2009/09/proof-1-something-else-is-needed.html


CURRENTLY ADDING

Proof 1: something else is needed....

Assume we are using a genetic algorithm, we want the perfect strategy in a game of 'Go'
'go' has way too many ways to play it for a computer to calculate (just consider it too many to be practical to solve)

1. the perfect strategy beats all other strategies
2. If you learn from experience alone, you may only be equiped to handle experiences you have been exposed to
3. Selection is made by the ability to handle experiences
4. ability to handle experience depends on genes
5. which genes have survived, depends on what events or experiences has lead to that point
6. genes represent past experience (3,4,5)
7. if you only learn by experiences, you must be exposed to all experiences to become perfect (1,6)
8. to become perfect more than experience is needed OR nearly all experiences must be encountered.
(assumed there was too many experiences)
9. more than experience is needed (8+assumption)
10. genes are not enough OR genes must represent more than experience (edit) OR perfection is impossible, maximizing is necessary

Balance and perfection

Basic genetic algorithms are very simple in my opinion. However, it has become apparent that the way they are tested and selected can determine how well the outcome is. Naturally, one might think that simply choosing the best based on how it faces against the rest of the population, or some standard.

The problem with choosing one standard for the program to beat, is that the single standard may not be as good as it can get. Perhaps there are other scenarios that the algorithms will not be able to handle that were never presented.

To fix this problem I decided to make the population play against each other, that way they are exposed to many strategies.... but there is a much more interesting problem with this

If the population fight against itself, there is the possibility it will keep going until something reaches the perfect algorithm, and then the gene pool is dominated by it.

However, there is a much much much more probable scenario.
Perhaps the system will improve consistently, but only until the system reaches Balance. what if it gets to the point where all the algorithms seem to do equally well as each other, not exactly, but enough to significantly stall the process. for instance, some strategies may develop that are counters to other organisms strategies, but these strategies are all intertwined in some simple or not so simple order. These strategies will always beat each other out and play out in the same way. An equilibrium will be established, nothing will truly improve as one cannot say which of these strategies are truly 'better'

There has to be a way to shake up the balance, perhaps my random idea will be enough, but I must consider the probable fact that it will not. What can make the balance fall apart without abandoning strategies completely?

how neatly done!

Typical genetic algorithm:
specific traits are chosen very carefully, as the computer scientist approaches the problem. A specific string of binary numbers is chosen to represent his creation. These numbers will mutate to perform the task at hand. In order for this scientist to do so, he must test how well each binary code will do in the given scenario, so that the scientist may more carefully decide which one is correct.

There is tedious calculation, each may be given multiple scenarios, then ranked on how well each binary code performs. They use advanced math to decide how each one should be chosen, and how many children each binary string should have, or whether they should die.

Then when the scientist runs this program, something happens. There is a 'super subject' but not in a good way. This subject is not getting better, but it's gene's are dominating the gene pool. This super subject is not as perfect as we would like, so much more mathematical calibration must be done.



Well, what if the scientist did something else....
A lot of times in real life, some things that happen seemingly randomly give us an advantage. While over time the strongest survive, some of the weaker ones survive and keep traits that may become useful. We need the weak and the strong, and some way to choose between them.

Well, what if they competed against each other, and we recorded how many times they win. However, not all of them will necessarily get to play the same amount, each one is randomly chosen as a pair to fight, then on to the next pair. There are a lot of pairings, and yes it is a bit random, but those who are better over time will succeed....

let's see what happens!!!

no, i did not read this over before i posted it

I have reason to believe my first version of this program I am making will completely fail. Why??

Well this first version will be missing at least one key aspect of logic/math

mathematics within logic:
currently, the program may only consider a variable, and its relationship with another varible. not the variable minus 1 compared to the other variable, or the variable minus some other variable compared to a variable.... it's strictly variable to variable comparison. This is a problem because:
Imagine we're playing a 'game':
I give you three numbers, A, B, and C.
I want you to tell me whether or not A minus B is greater than C

the logic you would do is as follows
if(A-B > C)
Say "yes"
However my program cannot do that, it cannot subtract A-B and compare it to C

Now imagine you are intelectually limited to variable by variable comparison
There's no way to determine for certain whether or not A -B is greater than C, the closest you can get is:
if(A > B and A > C)
say "yes"
However, there are numerous counterexamples, so you would not be correct 100% of the time. (example A=5 C=2, B=2, 5-2 is not greater than 2)

What's the solution??
well.... I have half of an idea... I think i can do it... implementing it may turn my own head upsidedown

independent calculators:
These calculators will take multiple variables, they can be any particular variables that the neuron may decide, and do math ONLY with those numbers. Not any other input, just the variables given. However, how these will be implemented may be another story. I may find that each part of the if statement, I may need to make an object that is an independent calculator. Then the question may become-- should these independent calculators only be within the neuron, or should the entire brain have access to these calculators?

I think yes, with all neurons able to call on independent calculators, they may find that the calculators will become to represent rules in whichever game it is trying to learn. These rules may end up being used to solve different games it may try to learn.

Why is this so hard?????
first off, they are one more thing to mutate. I already have to mutate how the brain works, then how each neuron works, now I need to worry about mutating these guys.
The neuron also needs to recognize that these calculators exist, then mutate what they choose to put in the calculators.

Ahh yes it is tommorrow

Okay, so assuming the first program works well, I will naturally want to make it better

What I have made with the little 'neurons' communicating will now come in handy. They are very flexible objects, they can make connections based on their own logic, and if the first project works, it will be able to do this really well for one game.

Now, what if I wanted my program to learn 2 different games?

The second step of this project will be to allow the program to learn 2 games, by re-using some of the same neurons!! This is something that to my understanding is something a genetic algorithm cant do. Can one genetic algorithm learn to play different games, yes, but they cant do it with the same gene! (again, to my understanding).

There is a challenge to this, all input is different for each game, and these neurons are only set in to take a specific input. The problem is, how does it assign variables to spots that are missing? Well, the program is going to need to mutate to find this out (for now). It will be able to call on a neuron that uses a different game's logic, and will assign it variables randomly. Further progressions would be to have a logic for assigning these variables.... how I am not sure yet but I do already have a few ideas.... which I will write about another time...

okay updates WILL come more frequently!!!

For the past few days I have been contemplating what my little program may be able to do, and how to improve it.

Here's the game plan
The first program I will write, will be able use logic and math combined to have a final outcome. The logic will be solid once the mutated being is created, this is not to say that it will react the same way in a given situation (as it may consider a random variable), but that it will always consider the same variables.

This program may be capable of creating logic in a algorithm differently than any way I have researched. There are different 'neurons' each with their own set of logic that is set to take in certain input, either from other 'neurons' or the input given. (all input is in form of numbers). This may allow a few neurons to concentrate on what strategy is best, it may also condense information to a more usable form before the initial processing. the condensing of information will allow faster processing, however the only way for me to ensure that this can happen is if i not only select which algorithms are best on the ability to solve the problem, but also its efficiency. Efficiency of algorithms does not seem to come in play in other methods of genetic algorithms, as they always have the same efficiency the way it is set up.

Tommorow... What I want the next program to be able to develope to.... much closer to something may be able to think like us...

I would like anybody reading this to keep in mind I am being very theoretical here-- really more like experimental with what the actual capabilities of the program will be. I am assuming if I give the program near infinite flexibility, as well as the ability to be selected on efficiency, it will evolve into something that can effectively solve multiple problems, just like we came about. If nothing else this will be fun, after all I am very young :-)

Since the last time

It has been a short while since I posted last, and as such I have a lot of changes to what I plan on doing.

My previous idea with the hierarchy of voting, has been nearly forgotten, maybe I'll try it out if this doesn't work.

However If my newer Idea works, it has the potential of not only beating people at one game, but many with the same algorithm

This idea does not only use math, but a heck of a lot more logic. For every piece of math done, there will be an option for a logical requirement to do that math... So it will work something like this

Each 'logic machine' will get an array of variables
vars[]
then a stream of logic and math will follow, this will be encoded somewhat, but just for the sake of making it easier to understand.

if(vars[1]>vars[0])
finalVar = 1 // could be subtracting, adding, multipliing, adding a variable

'finalVar' will be what the algorithm returns to whatever gave them the vars.
with this, things get interesting

the algorithms can give each other their calculations. How they do that is in my head and still needs perfection... and hey if this really ends up working out (on the off chance) I gotta keep part of it secret!!

This is fun!!!

I am very behind in ideas, So I will start with what I will be working on over the summer

My original genetic algorithm I wrote way before summer, had some sort of a mutating math algorithm trying to figure out where the right place is to go.

Most recently, I have realized it may not be the best to only have ONE math equation, but maybe an organized series, or even hierarchy of them... working as follows

A math equation at first is the only decider for the ultimate decision. But let's say it mutates and copies itself slightly off, and actually makes two deciders, so the decision chart looks as so.... (d, decision, m Math equation)

....d
.../ \
.m...m
Each math equation 'votes' to the final decision of where to move (each line in these charts will represent one vote). Iff (not a typo, iff = 'if and only if') there is a tie, the math equations will compare the priority they assigned their decision, and move as to who assigned highest priority (alrighty in my math equation)

Now needless to say, there could be any number of Math equations making one decision, but things get more complicated....

Now let's say one math equation on one part of the brain just cant assign its vote accuratly with only one equation (really just under random mutation....) it can split off as well, decision chart as follows

......d
..../....\
..m .....d
........../ \
........m...m
Hopefully, this will allow my little mutant math equations to express themselves better, and just make better decision, however my new laptop might die trying to do it......

full time job + programming = fun

So I have had time to think about a nice new fun idea, partially inspired by our own brain. I have been thinking about my mutation program, the one with a genetic algorithm where the little guys fight to the death to see who is better at a game of connect four. Well, their brains are unchallenged, they make one decision they are never torn. So, what if their brains were allowed to split into two mutating wonders, that would argue, or even 3. Sure they would not really completely argue, but rather vote as to which one they want to go to, and whichever one thinks louder (I swear there's math behind it, they use priority....) will decide the movement. I am interested how it will turn out.

Newest inspiration:
Tide wars: a (real life) game where one uses beach objects to try and protect one's fort against the tide's rage. When Creating a fence with two layers of sticks, spaced apart appropriately, One can fit big and small rocks and such in between. As the water moves along the rocks, the rocks that do not fit/ are too small, will eventually wash away, those that are not, will become wedged in just the right spot. What if a logic organism could develop that way?

Newest random idea:
Using binary genetic bits, the genetic bits should not only be mutated, but maybe the way that the organism interprets it's gene's could be mutated either while in life or the interpretation can be a genetic trait as well. Perhaps one could go deeper, and allow the organism to interpret differently with in it's life according to some algorithm that takes in positive/negative stimuli, and the way that stimuli effects the interpretation of gene is also mutated.

I realize I am stuck on mutating algorithms, I also realize I should find more, however for now I cannot get my own mind off of it, as it seems the best way humans could make something smarter than themselves without having to overcome any huge intelligence leaps.

Perhaps there is another more controllable way to deal with it, maybe it will use an integration of all sorts of methods, I want to map out or organize the methods and look at the pros/cons and just try to mix a couple and see how it turns out. ... I still want a mutating learning algorithm... just cant find a learning algorithm that isn't so straight forward.

Thought

I havent forgottaen about this just had busy 4 months... breif ideas for the day i must elaborate on later

fractal learning as taking something you think and keep puting that back into the thought process over and over

computer feeling through the system and developing senses using assembly. or making a complex virtual environment where senses may be developed.

seeing changes in data may help developing senses. (we typically sense things that change a lot and that are statistically useful for survival.)

making it possible for the math going on inside the brain or thought process to not only be linear thoughts, but ones that may be turned in to multi-dimensional, or even plug values into itself (fractal)

Evolution

I honestly did not think I would get this far in my highschool year-- I either underestimated myself or overestimated the problem. I have had this idea existing for the past couple days, and it has been working for least least 4 days, and in this time I have tried to explain how this program works to many people, here's what I've practiced.

This program tries to play Connect4. There is an equation the program uses to try and figure out which spot is the best. Now you will notice that I used the word, 'try' alot, that's because it's never certain. The program's equation actually mutates. It copies itself and adds a slight mutation, then all of them play Connect4 a couple times to decide which mutations are best, and those live on while the rest die. The living ones reproduce and it goes on and on.

So far the equation it has is far from perfect, my challenge is to give it an opponent, my best choice I figure is to get them to play each other, I am experimenting with that right now.

I will post the advances I make but for some reason I feel as though I've stumbled on something I almost want to keep it somewhat private, so my descriptions will be vague...

contact me dfreelan@gmail.com if you want to know more (not that I have many followers...)

Connect 4

I tried to use the same algorithm I did with Tic-Tac toe on Connect four, and i ran into some problem with memory---

actually i never explained how i got tic-tac-toe to work... it actually was an interesting story...

So as the game plays against itself over and over again, it records what spaces lead to losses, what moves lead to wins, and what moves lead to ties. There is then a statistic taken every turn to see which one is the best, and the statistics are constantly updated. However it is a bit more than statistics, hardly but distinct, i programmed a "gullibility factor", well that's what I call it. the wins could only possibly get up to 10, or whatever the 'gullibility factor' was and it could only get so bad as the gullibility factor.

Now dealing with ties is where something interesting happened, when both computers saw ties as a form of winning, both of them simply made the same moves over and over again, not surprising. When both computers considered them loses , when they played against a human they failed, they would choose to lose instead of tie sometimes.

However when one computer considered ties wins, and the other one considered ties loses, one of them succeeded. To me it seemed like a pessimist vs optimist situation, and i believe the optimist won this round. Because the program considered ties wins and the others loses, the one that thought they were loses continually changed strategy, while the other one was able to learn and find all the different possibilities of winning. While the loser, simply ended up moving randomly in the end when you try to go against it.

Now I need to do something with Connect 4, but there are too many combinations, and the RAM just cant take it on any computer I can come in contact with. So Now I must come up with a new strategy, I think I will come up with it tomorrow.... lots of thinking to do

Alright I missed a couple.

I over the passed couple days made a program that I taught to play tic-tac-toe. It is about 1000 lines of code devoted to trying to get it to learn to play tic-tac-toe better and better with experience. So I skipped out on writing.

I was recently contemplating the need for speech to communicate and speak, I was wondering if one were to master thinking without language and think about AI one might get a better understanding of how to understand what language is, and how to program it.

To be continued...