Difference between revisions of "Colin Kern"
| Line 1: | Line 1: | ||
| − | + | == Abstract == | |
| + | I am going to create neural net software and design a neural net that can learn to play Tic Tac Toe. The net will receive the game board as its input (probably nine nodes for each square) and output the square it will put its symbol in. This could be represented as either one node outputting a number corresponding to a certain square or nine nodes each outputting a number, the largest (or smallest) of which is the preferred square. I will have to experiment to see which of these methods (and perhaps others I can think of) work and how well they work. The performance of a neural net can be measured by how fast the net reaches its maximum learning capacity and how correct that capacity is. | ||
| + | ---- | ||
| + | |||
| + | == Journal == | ||
| + | '''September 13, 2005''' | ||
| + | |||
| + | I finished my abstract, but I'm having trouble getting excited about simply creating a neural net and teaching it to play Tic Tac Toe. I don't know how complicated that will turn out to be, so I don't know if I have the time to do anything more. I've had two ideas that might make the project more interesting. | ||
| + | |||
| + | First, I could try to make the neural net code I write able to support as many different kinds of neural nets as possible. I'd just write the basic data structures and algorithms, then write a program that takes a file specifying the shape of the neural net and creates the net from that. It can then take other input, such as the algorithm to use for training and a training script. A user would issue a command similar to "./neuralnet structure.txt algorithm.txt training.txt net.txt". This would create the neural net in structure.txt and train it using algorithm.txt and training.txt. The trained net would be output to net.txt. Another command, "./neuralnet net.txt", would load the trained net and stdin would be the input given to the net, whose output would be written to stdout. | ||
| + | |||
| + | The other idea is to experiment with a neural net's ability to learn grammars. Give it strings such as 'ab', 'aabb', 'aaabbb' that are in the grammar and 'a', 'abb', 'aba' that aren't, then see if it can correctly say whether other strings are also in the grammar. It would be interesting to see what grammars can be learned and how adding more layers to a perceptron would increase the complexity of the grammars that can be learned. A complication I see is how to input variable length strings. I can see either having a large set of input nodes, some of which aren't used, or giving the net the string one character at a time and the net saying "yes" or "no" for each character (and if it is still saying yes on the last character, it accepts the string). | ||
| + | |||
| + | I'd probably be more interested in doing the second of these ideas. | ||
| + | ---- | ||
Revision as of 21:56, 13 September 2005
Abstract
I am going to create neural net software and design a neural net that can learn to play Tic Tac Toe. The net will receive the game board as its input (probably nine nodes for each square) and output the square it will put its symbol in. This could be represented as either one node outputting a number corresponding to a certain square or nine nodes each outputting a number, the largest (or smallest) of which is the preferred square. I will have to experiment to see which of these methods (and perhaps others I can think of) work and how well they work. The performance of a neural net can be measured by how fast the net reaches its maximum learning capacity and how correct that capacity is.
Journal
September 13, 2005
I finished my abstract, but I'm having trouble getting excited about simply creating a neural net and teaching it to play Tic Tac Toe. I don't know how complicated that will turn out to be, so I don't know if I have the time to do anything more. I've had two ideas that might make the project more interesting.
First, I could try to make the neural net code I write able to support as many different kinds of neural nets as possible. I'd just write the basic data structures and algorithms, then write a program that takes a file specifying the shape of the neural net and creates the net from that. It can then take other input, such as the algorithm to use for training and a training script. A user would issue a command similar to "./neuralnet structure.txt algorithm.txt training.txt net.txt". This would create the neural net in structure.txt and train it using algorithm.txt and training.txt. The trained net would be output to net.txt. Another command, "./neuralnet net.txt", would load the trained net and stdin would be the input given to the net, whose output would be written to stdout.
The other idea is to experiment with a neural net's ability to learn grammars. Give it strings such as 'ab', 'aabb', 'aaabbb' that are in the grammar and 'a', 'abb', 'aba' that aren't, then see if it can correctly say whether other strings are also in the grammar. It would be interesting to see what grammars can be learned and how adding more layers to a perceptron would increase the complexity of the grammars that can be learned. A complication I see is how to input variable length strings. I can see either having a large set of input nodes, some of which aren't used, or giving the net the string one character at a time and the net saying "yes" or "no" for each character (and if it is still saying yes on the last character, it accepts the string).
I'd probably be more interested in doing the second of these ideas.
