Convolution Neural Network - Autoencoder

This is a use case of DEATF where a convolutional Autoencoder is used.

In order to create that Autoencoder both CNN and TCNN are used. This is an unsupervised problem, where the objective is reducing the dimensionaly of the data. The CNN wil be responisble of reducing the dimension and the TCNN of returning it into its original form.

cnn_ae.eval_cnn_ae(nets, train_inputs, _, batch_size, iters, test_inputs, __, hypers)

In order to evaluate the Autoencoder, as an MLP descriptor is used, a Flatten layer is added before the network that is created. Then is trained using the defined mean square error and its final performance metric is also the mean squared error.

Parameters

• nets – Dictionary with the networks that will be used to build the final network and that represent the individuals to be evaluated in the genetic algorithm.

• train_inputs – Input data for training, this data will only be used to give it to the created networks and train them.

• train_outputs – Output data for training, it will be used to compare the returned values by the networks and see their performance.

• batch_size – Number of samples per batch are used during training process.

• iters – Number of iterations that each network will be trained.

• test_inputs – Input data for testing, this data will only be used to give it to the created networks and test them. It can not be used during training in order to get a real feedback.

• test_outputs – Output data for testing, it will be used to compare the returned values by the networks and see their real performance.

• hypers – Hyperparameters that are being evolved and used in the process.

Returns

Mean squared error obtained with the test data that evaluates the true performance of the network.