Genetic Algorithm and Neural Network

1
votes

Right now I'm doing a research about Genetic Algorithm and Neural Network, I want to use the Genetic Algorithm to train the Neural Network and use the Neural Network to solve OCR problem, what I'm still don't understand is the training method, let's say I have 5 training set each set have 26 character (A-Z), should I do the training from A1-Z1 to A5-Z5 (per set) or A1-A5 to Z1-Z5 (per character) and how many generations should be generated per character?or until the error is minimum?

I think that's all I want to ask right now

if is there anything unclear about my question please tell me

Thank You

3
artificial-intelligenceneural-networkgenetic-algorithm
This sounds like it has already been treated by hundreds of people. I don't see anything in your description that sounds new. Have you looked for and read some scientific papers on that subject? Google is a tremendously well working search engine. There are mentioning of Arabic and Hindi character sets. I would be totally surprised if this would be new for Latin. - Andreas
Yes it's not a whole new algorithm, I already read the paper you read about arabic and hindi set, what I want to try is to add another process (selecting the architecture) before the training using genetic algorithm but I still not sure how to select weight using genetic algorithm - Niko Adrianus Yuwono

3 Answers

1
votes

Actually, you really can develop a neural network for each letter. Just use Autoassociative Networks (Autoencoders). These networks are trained so that the output reproduces the input. That way you would train 26 networks. At validation time, for each letter, the network that obtains the lowest error is the network that represents the letter. This approach has achieved excellent results for classification problems.

0
votes

A neural network with 26 outputs is odd. You should build a network for each letter, but let it see all letters during training so it could tell you when it sees intended letter. For number of generations typically you should meet one of two conditions: Error becomes lower then a threshold or number of generations exceed a limit. It depends on you to choose these params.

0
votes

It will be very slowly to train ANN with GA. Maybe you should think for some hybrid approach. You will need to do a lot of image preprocessing before to feed data in the ANN. Also you will need to design your ANN very carefully. You should think about the size of input and the size of output. With GA you can optimize two things: 1. ANN topology or 2. ANN weights.