Training a Neural Network using Genetic Algorithm.
Here are the results obtained after training a neural net with both backpropagation and Genetic programming.
Trained using GP (on the training set):
![alt tag](https://raw.githubusercontent.com/yugrocks/Genetic-Neural-Network/master/GNN_training_set.png)
Trained using GP (Performance on the test set):
![alt tag](https://raw.githubusercontent.com/yugrocks/Genetic-Neural-Network/master/GNN_test_set.png)
Trained using Backprop (on the training set):
![alt tag](https://raw.githubusercontent.com/yugrocks/Genetic-Neural-Network/master/NN_training_set.png)
Trained using Backprop (Performance on the test set):
![alt tag](https://raw.githubusercontent.com/yugrocks/Genetic-Neural-Network/master/NN_test_set.png)
Loss/Cost (on training set) after 1000 generations: 0.2231
Training Set Accuracy: 90.24%
Test set Accuracy: 91.25%
The Backpropagation approach:
Loss/Cost (on training set) after 1000 epochs: 0.2528
Training Set Accuracy: 90.00%
Test set Accuracy: 89.62%