Deep Learning(3)

Linear Units in Keras

The easiest way to create a model in Keras is through 'keras.Sequential', which creates a stack of layers from a neural network. Of course, we can also use a dense layer to create the model.

We can define a linear model that takes three input features ('sugars', 'fiber', and 'protein') and then generate a simgle output ('calories') like this:

from tensorflow import keras
from tensorflow.keras import layers

# Create a network with 1 linear unit
model = keras.Sequential([
    layers.Dense(units=1, input_shape=[3])
])

With the first parameter, 'units' , we define how many outputs we want. In this case, we're just predicting 'calories', so we'll use 'units = 1'.

With the second parameter, 'input_shape', we tell Keras the dimension of the inputs. Setting 'input_shape=[3]' ensures that the model will accept three features as input ('sugars', 'fiber', and 'protein').

This model is now ready to be fit to training data