You have now seen the challenge I have placed before myself. I want to build a super computer for $500 or less. Why? I'm bored. The plan is to find all the parts and put it together without spending any more than $500.
Problem is, the cooling system I want will most likely be more than $500, so I'm going to be working hard to find the bargains.
Saturday, December 18, 2010
Thursday, October 28, 2010
RIP Numb3rs
It's just come to my attention that my favorite show of all time has been canceled. Numb3rs, a show that, frankly, made me fall in love with math is leaving our airwaves forever.
This saddens me. It's the show that got me interested in applied mathematics, the show that really made me want to learn how to use math in ways other than counting money and doing simple arithmetic.
Oh well, hopefully someone will come up with a movie or another show similar to Numb3rs.
This saddens me. It's the show that got me interested in applied mathematics, the show that really made me want to learn how to use math in ways other than counting money and doing simple arithmetic.
Oh well, hopefully someone will come up with a movie or another show similar to Numb3rs.
Monday, October 25, 2010
The Quest: Finding A PHD
So, I have recently decided to work towards my doctoral degree in Computer Science. This was a decision I made with half an ounce of regret and self loathing. See, I love to learn, yet I hate conventional classrooms, and it's very difficult for me to work on my own in an online college campus.
In the end though, I want to do this because I want...no, I need to prove to myself that I have it in me. It's the basis of this website. Questioning your brain. The title was derived from neural networks and artificial intelligence, but it works for this as well. You can't question anyone else if you are afraid to question yourself. So, from this day forward I have one major goal in mind. This is a goal that my wife has decided to stand beside me towards, and a goal that will lead to me being able to provide better for my son.
In the end, I can't see a downside to it.
Step 1 - Figure out what is required to become a PHD candidate.
In the end though, I want to do this because I want...no, I need to prove to myself that I have it in me. It's the basis of this website. Questioning your brain. The title was derived from neural networks and artificial intelligence, but it works for this as well. You can't question anyone else if you are afraid to question yourself. So, from this day forward I have one major goal in mind. This is a goal that my wife has decided to stand beside me towards, and a goal that will lead to me being able to provide better for my son.
In the end, I can't see a downside to it.
Step 1 - Figure out what is required to become a PHD candidate.
Friday, October 22, 2010
Inquisitiveness and Neural Networks
How do we learn? How is it that a human being is capable of going above and beyond being taught, and actually pilot the process of learning themselves?
We ask questions. We wonder. We question ourselves, and try to further our knowledge. A step forward in artificial intelligence is trying to find a way to get a computer to question itself, and then to find those answers, and if it can't find the answers for itself, it should ask us.
A computer needs to be like a child, a child like any other. It needs to play, and enjoy itself, and just live. That is how it will learn. We learn by doing, by seeing.
We learn, by living.
We ask questions. We wonder. We question ourselves, and try to further our knowledge. A step forward in artificial intelligence is trying to find a way to get a computer to question itself, and then to find those answers, and if it can't find the answers for itself, it should ask us.
A computer needs to be like a child, a child like any other. It needs to play, and enjoy itself, and just live. That is how it will learn. We learn by doing, by seeing.
We learn, by living.
Tuesday, October 19, 2010
What if?
What if you could teach a neural network Game Theory? What if you could teach it to look at a problem using Game theory, and have it give you the best answer based on what game theory teaches us? Combining these two methods may lead us to a new developments in artificial intelligence.
The Idea of a Neural Network having "Free Will"
It is clear to me that a neural network in it's current shape can never have free will. That is because neural networks are, on the large part, created to perform specific tasks. The idea of giving a neural network free will is impossible in this shape because that network is specifically tailored for one job, and knows nothing but that job.
To give a neural network true free will, we would need to develop a network that is capable of taking in every form of input and create decisions based on that. It should be able to take requests from us, but it should not be required to actually perform these requests. Much like a child, we need to give the network the ability to go against our wishes.
This will be a difficult task for even the most mild mannered developer. Why? Because it is a machine, and as all conventional logic dictates a machine is there to do our bidding. What I am proposing is not so much a slave to our commands, but a living being.
Free will is what separates us from the machines. It is what gives us our intelligence. We are free to learn, we are free NOT to learn. We are free to ignore facts and open our mind to unconventional beings. We are free to believe what we will, and have faith in religious icons.
Freedom is what is missing from artificial intelligence. And until freedom is fully realized in this field, true intelligence will never be synthesized.
To give a neural network true free will, we would need to develop a network that is capable of taking in every form of input and create decisions based on that. It should be able to take requests from us, but it should not be required to actually perform these requests. Much like a child, we need to give the network the ability to go against our wishes.
This will be a difficult task for even the most mild mannered developer. Why? Because it is a machine, and as all conventional logic dictates a machine is there to do our bidding. What I am proposing is not so much a slave to our commands, but a living being.
Free will is what separates us from the machines. It is what gives us our intelligence. We are free to learn, we are free NOT to learn. We are free to ignore facts and open our mind to unconventional beings. We are free to believe what we will, and have faith in religious icons.
Freedom is what is missing from artificial intelligence. And until freedom is fully realized in this field, true intelligence will never be synthesized.
Friday, October 15, 2010
Training a Neural Network to respond naturally
Hypothesis:
Using a combination of frequency analysis for word usage in every day speak (VIA trolling online web chats in things like IRC [internet relay chat] programs) and applying weights to aspects of the language such as:
*EDIT: October 17th, 2010*
I would further hypothesis that the use of recursion in this neural network would lead to a more stable output, and a better neural network in the long run.
Using a combination of frequency analysis for word usage in every day speak (VIA trolling online web chats in things like IRC [internet relay chat] programs) and applying weights to aspects of the language such as:
- Location in phrase
- Location in conjunction to punctuation
- Location and frequency to adjoining words (such as “do this now” this is adjoined by “do” and “now”)
- Timing to previous statements (if “What’s good” is closely followed by “Everything, how’s you?” and given a weight, it would be a good assumption that the two are interrelated and one is a response to the other)
*EDIT: October 17th, 2010*
I would further hypothesis that the use of recursion in this neural network would lead to a more stable output, and a better neural network in the long run.
Subscribe to:
Posts (Atom)