Mdl = fcnntrain (…) requires the following input arguments.

• X : An $N\times M$ matrix containing the data set to be trained upon. Rows $N$ correspond to individual samples and columns $M$ correspond to features (dimensions). Type of X must be double.
• Y : An $N\times 1$ column vector containing the labels of the training dataset. The labels must be natural numbers (positive integers) starting from 1 up to the number of classes, similarly as returned by the ‘grp2idx‘ function. Type of Y must be double.
• LayerSizes : A numeric row vector of integer values defining the size of the hidden layers of the network. Input and output layers are automatically determined by the training data and their labels.
• Activations : A numeric row vector of integer values defining the activation functions to be used at each layer including the output layer. The corresponding codes to activation functions is:
  • 0 : 'Linear'
  • 1 : 'Sigmoid'
  • 2 : 'Rectified Linear Unit (ReLU)'
  • 3 : 'Hyperbolic tangent (tanh)'
  • 4 : 'Softmax'
  • 5 : 'Parametric or Leaky ReLU'
  • 6 : 'Exponential Linear Unit (ELU)'
  • 7 : 'Gaussian Error Linear Unit (GELU)'
• NumThreads : A positive scalar integer value defining the number of threads used for computing the activation layers. For layers with less than 1000 neurons, NumThreads always defaults to 1.
• Alpha : A positive scalar value defining the parameter alpha used in ReLU and ELU activation layers.
• LearningRate : A positive scalar value defining the learning rate used by the gradient descend algorithm during training.
• Epochs : A positive scalar value defining the number of epochs for training the model.
• DisplayInfo : A boolean scalar indicating whether to print information during training.

fcnntrain returns the trained model, Mdl, as a structure containing the following fields:

• LayerWeights : A cell array with each element containing a matrix with the Weights and Biases of each layer including the output layer.
• Activations : A numeric row vector of integer values defining the activation functions to be used at each layer including the output layer.
• Accuracy : The prediction accuracy at each iteration during the neural network model’s training process.
• Loss : The loss value recorded at each iteration during the neural network model’s training process.
• Alpha : The value of the Alpha parameter used in ReLU and ELU activation layers.

Installation Note: in order to support parallel processing on MacOS, users have to manually add support for OpenMP by adding the following flags to CFLAGS and CXXFLAGS prior to installing the statistics package:

setenv ("CPPFLAGS", "-I/opt/homebrew/opt/libomp/include -Xclang -fopenmp")

See also: fcnnpredict, fitcnet, ClassificationNeuralNetwork

Source Code: fcnntrain