This is documentation for Orange 2.7. For the latest documentation, see Orange 3.

Neural Network Learner (neural)

class Orange.classification.neural.NeuralNetworkLearner(name=NeuralNetwork, n_mid=10, reg_fact=1, max_iter=300, normalize=True, rand=None)

Bases: Orange.classification.Learner

NeuralNetworkLearner implements a multilayer perceptron. Learning is performed by minimizing an L2-regularized cost function with scipy’s implementation of L-BFGS. The current implementations is limited to a single hidden layer.

Regression is currently not supported.

  • name (string) – learner name.
  • n_mid (int) – Number of nodes in the hidden layer
  • reg_fact (float) – Regularization factor.
  • max_iter (int) – Maximum number of iterations.
  • normalize (bool) – Normalize the data prior to learning (subtract each column by the mean and divide by the standard deviation)
Return type:

NeuralNetworkLearner or NeuralNetworkClassifier

__call__(data, weight=0)

Learn from the given table of data instances.

Return type:


class Orange.classification.neural.NeuralNetworkClassifier(domain, nn, normalize, mean, std, **kwargs)

Bases: Orange.classification.Classifier

Classifier induced by the NeuralNetworkLearner.

__call__(example, result_type=0)
  • example ( – instance to be classified.
  • result_typeOrange.classification.Classifier.GetValue or Orange.classification.Classifier.GetProbabilities or Orange.classification.Classifier.GetBoth
Return type:, Orange.statistics.Distribution or a tuple with both