Predefined MLP

test_mlp.test_MLP_all_datasets(eval_func=None, batch_size=150, population=5, generations=10, iters=100, max_num_layers=10, max_num_neurons=20, evol_alg='mu_plus_lambda', sel='best', lrate=0.01, cxp=0, mtp=1, seed=None, sel_kwargs={}, max_filter=4, max_stride=3)

Tests the MLP network with all the possible datasets and with the specified parameter selection.

Parameters

  • eval_func – Evaluation function for evaluating each network.

  • batch_size – Batch size of the data during the training of the networks.

  • population – Number of individuals in the populations in the genetic algorithm.

  • generations – Number of generations that will be done in the genetic algorithm.

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

  • max_num_layers – Maximum number of layers allowed in the networks.

  • max_num_neurons – Maximum number of neurons allowed in the networks.

  • max_filter – Maximum size of the filter allowed in the networks.

  • max_stride – Maximum size of the stride allowed in the networks.

  • evol_alg – Evolving algorithm that will be used during the genetic algorithm.

  • sel – Selection method that will be used during the genetic algorithm.

  • sel_kwargs – Arguments for selection method.

  • lrate – Learning rate that will be used during training.

  • cxp – Crossover probability that will be used during the genetic algorithm.

  • mtp – Mutation probability that will be used during the genetic algorithm.

  • seed – Seed that will be used in every random method.

test_mlp.test_MLP(dataset_name, eval_func=None, batch_size=150, population=5, generations=10, iters=100, max_num_layers=10, max_num_neurons=20, evol_alg='mu_plus_lambda', sel='best', lrate=0.01, cxp=0, mtp=1, seed=None, sel_kwargs={}, max_filter=4, max_stride=3)

Tests the MLP network with the specified dataset and parameter selection.

Parameters

  • dataset_name – Name of the dataset that will be used in the genetic algorithm.

  • eval_func – Evaluation function for evaluating each network.

  • batch_size – Batch size of the data during the training of the networks.

  • population – Number of individuals in the populations in the genetic algorithm.

  • generations – Number of generations that will be done in the genetic algorithm.

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

  • max_num_layers – Maximum number of layers allowed in the networks.

  • max_num_neurons – Maximum number of neurons allowed in the networks.

  • max_filter – Maximum size of the filter allowed in the networks.

  • max_stride – Maximum size of the stride allowed in the networks.

  • evol_alg – Evolving algorithm that will be used during the genetic algorithm.

  • sel – Selection method that will be used during the genetic algorithm.

  • sel_kwargs – Arguments for selection method.

  • lrate – Learning rate that will be used during training.

  • cxp – Crossover probability that will be used during the genetic algorithm.

  • mtp – Mutation probability that will be used during the genetic algorithm.

  • seed – Seed that will be used in every random method.

Returns

The last generation, a log book (stats) and the hall of fame (the best individuals found).