"NeuralNetwork" (Machine Learning Method)

Details & Suboptions

  • A neural network consists of stacked layers, each performing a simple computation. Information is processed layer by layer from the input layer to the output layer. The neural network is trained to minimize a loss function on the training set using gradient descent.
  • The following options can be given:
  • MaxTrainingRoundsAutomaticthe maximum training rounds before training stops
    "ActivationFunction"Automaticthe activation function to use between layers
    "L2Regularization"Automaticthe parameter multipling the L2 term
    "NetworkType"Automaticthe type of network module to use
    "NetworkDepth"Automaticthe depth of the network
    "NumberOfParameters"Automaticthe total number of the network's trainable parameters
    "OptimizationMethod"Automaticthe optimization method to use during training
  • Possible settings for "NetworkType" include:
  • "FullyConnected"neural network based on LinearLayer
    "Convolutional"neural network based on ConvolutionLayer
    "Recurrent"neural network based on recurrent layers
  • Possible settings for "ActivationFunction" include:
  • Rampthe Ramp function
    LogisticSigmoidthe LogisticSigmoid function
    Tanhthe Tanh function
  • Possible settings for "OptimizationMethod" include:
  • "ADAM"stochastic gradient descent using an adaptive learning rate that is invariant to diagonal rescaling of the gradients
    "SGD"ordinary stochastic gradient descent with momentum

Examples

open allclose all

Basic Examples  (2)

Train a classifier function on labeled examples:

In[1]:=
Click for copyable input
Out[1]=

Look at its ClassifierInformation:

In[2]:=
Click for copyable input
Out[2]=

Classify a new example:

In[3]:=
Click for copyable input
Out[3]=

Generate some data and visualize it:

In[1]:=
Click for copyable input
Out[1]=

Train a predictor function on it:

In[2]:=
Click for copyable input
Out[2]=

Compare the data with the predicted values and look at the standard deviation:

In[3]:=
Click for copyable input
Out[3]=

Options  (6)

See Also

Classify  Predict  ClassifierFunction  PredictorFunction  ClassifierMeasurements  PredictorMeasurements  ClassifierInformation  PredictorInformation  SequencePredict  ClusterClassify

Related Demonstrations

Related Methods