Neural Network Projects with Python

Model training

To train our MLP model defined in earlier steps, let's call the fit function. Let's train our model for 200 iterations:

# Train the model for 200 epochsmodel.fit(X_train, y_train, epochs=200)

We get the following result:

As we can see, the loss decreases and the accuracy increases over each epoch, as the learning algorithm continuously updates the weights and biases in the MLP according to the training data. Note that the accuracy shown in the preceding screenshot refers to the accuracy based on the training data. In the next section, we will take a look at the performance of the MLP based on the held out testing data, as ...