Hands-On Machine Learning for Algorithmic Trading

Defining the decoder

The decoder consists of the last autoencoder layer, fed by a placeholder for the encoded data:

encoded_input = Input(shape=(encoding_size,), name='Decoder_Input')decoder_layer = autoencoder.layers[-1](encoded_input)decoder = Model(inputs=encoded_input,                outputs=decoder_layer)decoder.summary()_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
Decoder_Input (InputLayer)   (None, 32)                0 _________________________________________________________________ Decoder (Dense) (None, 784) 25872 ================================================================= Total params: 25,872 Trainable params: 25,872 Non-trainable params: ...