Experimenting with wider networks

Now you know everything you need to begin experimenting with different models!

A model called model_1 has been pre-loaded. You can see a summary of this model printed in the IPython Shell. This is a relatively small network, with only 10 units in each hidden layer.

In this exercise you'll create a new model called model_2 which is similar to model_1, except it has 100 units in each hidden layer.

After you create model_2, both models will be fitted, and a graph showing both models loss score at each epoch will be shown. We added the argument verbose=False in the fitting commands to print out fewer updates, since you will look at these graphically instead of as text.

Because you are fitting two models, it will take a moment to see the outputs after you hit run, so be patient.

This exercise is part of the course

Introduction to Deep Learning in Python

View Course

Exercise instructions

Create model_2 to replicate model_1, but use 100 nodes instead of 10 for the first two Dense layers you add with the 'relu' activation. Use 2 nodes for the Dense output layer with 'softmax' as the activation.
Compile model_2 as you have done with previous models: Using 'adam' as the optimizer, 'categorical_crossentropy' for the loss, and metrics=['accuracy'].
Hit 'Submit Answer' to fit both the models and visualize which one gives better results! Notice the keyword argument verbose=False in model.fit(): This prints out fewer updates, since you'll be evaluating the models graphically instead of through text.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Define early_stopping_monitor
early_stopping_monitor = EarlyStopping(patience=2)

# Create the new model: model_2
model_2 = ____

# Add the first and second layers
____.____(____(____, ____=____, input_shape=input_shape))
____

# Add the output layer
____

# Compile model_2
____

# Fit model_1
model_1_training = model_1.fit(predictors, target, epochs=15, validation_split=0.2, callbacks=[early_stopping_monitor], verbose=False)

# Fit model_2
model_2_training = model_2.fit(predictors, target, epochs=15, validation_split=0.2, callbacks=[early_stopping_monitor], verbose=False)

# Create the plot
plt.plot(model_1_training.history['val_loss'], 'r', model_2_training.history['val_loss'], 'b')
plt.xlabel('Epochs')
plt.ylabel('Validation score')
plt.show()

Edit and Run Code