Hands-On Machine Learning for Algorithmic Trading

Defining the enoder

The encoder just uses the input and hidden layer with about half of the total parameters:

encoder = Model(inputs=input_ ,                outputs=encoding,                name='Encoder')encoder.summary()_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
Input (InputLayer)           (None, 784)               0         
_________________________________________________________________
Encoder (Dense)              (None, 32)                25120     
=================================================================
Total params: 25,120
Trainable params: 25,120
Non-trainable params: 0
_________________________________________________________________

Once we train the autoencoder, we can use the encoder to ...