No self-introduction
Loading
Profile
Follow
codes (1)
Genetic algorithm to train the weights of a neural
no vote
Takes a text file as input that contains the x and y coordinates of a series of points on a curve. The code then uses a genetic algorithm to train a neural network to approximate the same curve. Runs from the python command line; an example input command would look like: python nn_weights_1.py -r 10 -n 100 -g 500 -t 3600.0 -a RandomCrossOver -s random_seeds_100.txt -i sine_datapoints1.txt -o results.txt where nn_weights_1.py is the name of the code file, -r tells it how many runs to perform, -n tells it how many individuals are in the population, -g tells it how many generations in each run, -t tells it a maximum time to run (in seconds),
paulmunn 0 0
1
No more~
Follows0
Fans0