Multi-Network

This is a use case of DEATF where a mutiobjective problem is treated.

In order to face that problem, two MLPs are used. One will be responsible of classifying the MNIST dataset and the other one of doing it with the fashion MNIST dataset. Both are in the same model, but they work separately and do not interact between them in any moment.

multi.evaluation(nets, train_inputs, train_outputs, batch_size, iters, test_inputs, test_outputs, _)

In this caxe two simple MLPs are declarated and added to the model but with different inputs and outputs, so they are separated. Both training and testing will be done with different data and two final results will be obtained from the evaluation of the model.

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

Two accuracy errors, one from each MLP in the model.