"NeuralNetwork" (Machine Learning Method)
- Method for Classify and Predict.
- Models class probabilities or predicts the value distribution using a neural network.
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:
MaxTrainingRounds Automatic the maximum training rounds before training stops "ActivationFunction" Automatic the activation function to use between layers "L2Regularization" Automatic the parameter multipling the L2 term "NetworkType" Automatic the type of network module to use "NetworkDepth" Automatic the depth of the network "NumberOfParameters" Automatic the total number of the network's trainable parameters "OptimizationMethod" Automatic the 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:
Ramp the Ramp function LogisticSigmoid the LogisticSigmoid function Tanh the 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
Examplesopen allclose all
Basic Examples (2)
Look at its ClassifierInformation: