Python Deep Learning Projects

Building and training a simple deep neural network

Now that we have loaded the data into memory, we need to build a simple neural network model to predict the MNIST digits. We will use the same architecture we used in Chapter 2, Training NN for Prediction Using Regression.

We will be building a Sequential model. So, let's import it from Keras and initialize it with the following code:

from keras.models import Sequentialmodel = Sequential()

To learn more about the Keras Model API, visit https://keras.io/models/model/.

The next thing that we need to do is define the Dense/Perceptron layer. In Keras, this can be done by importing the Dense layer, as follows:

from keras.layers import Dense

Then, we need to add the Dense layer to the Sequential ...