Hello nets!
You're going to build a simple neural network to get a feeling of how quickly it is to accomplish this in Keras.
You will build a network that takes two numbers as an input, passes them through a hidden layer of 10 neurons, and finally outputs a single non-constrained number.
A non-constrained output can be obtained by avoiding setting an activation function in the output layer. This is useful for problems like regression, when we want our output to be able to take any non-constrained value.

This exercise is part of the course
Introduction to Deep Learning with Keras
Exercise instructions
- Import the
Sequential
model fromtensorflow.keras.models
and theDense
layer fromtensorflow.keras.layers
. - Create an instance of the
Sequential
model. - Add a 10-neuron hidden
Dense
layer with aninput_shape
of two neurons. - Add a final 1-neuron output layer and summarize your model with
summary()
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Import the Sequential model and Dense layer
from tensorflow.keras.____ import ____
from tensorflow.keras.____ import ____
# Create a Sequential model
model = ____
# Add an input layer and a hidden layer with 10 neurons
model.add(Dense(____, input_shape=(____,), activation="relu"))
# Add a 1-neuron output layer
model.add(____)
# Summarise your model
model.____