Reminder – Why Not Use A Genetic Algorithm For Machine Learning Generation

Just a quick idea. I thought I use pyevolve ( genetic algorithm – python module ) to see if I could generate an image from a machine learning network. I thought I have a classifier which I would get some real valued number from (going to strip the binary function in the end). This indication is going into the genetic algorithm as a score. Then the algorthm generates new guesses which will be selected from.

Its my project for this time.

Have not got around to testing. But I found out something interesting. Using the handwritten digits I manage to get much better accuracy for the digit recognition from adding noise digits and classifying them as their own special number.

Thats is. I added 180 numpy.random.rand(8,8) matrices to the digits random images. After training. The 180 random images were recognized as the number 77 and the other numbers got better at their recognition.

(Visited 23 times, 1 visits today)