DNNClassifier - Maple Help

DeepLearning

 DNNClassifier
 construct a neural network classifier

 Calling Sequence DNNClassifier(fc,opts)

Parameters

 fc - list of feature columns opts - (optional) one or more keyword options described below

Options

 • hidden_units : list of nonnegative integers
 Specifies the number of hidden nodes in the neural network at each level.
 • num_classes : nonnegative integer
 Specifies the number of distinct classes into which the data should be classified.
 • optimizer : function or Optimizer object
 Specifies the optimizer to use to train the model. The default is the Adagrad optimizer.

Description

 • The DNNClassifier(fc,opts) command creates a deep neural network classifier for the feature columns specified in fc.
 • This function is part of the DeepLearning package, so it can be used in the short form DNNClassifier(..) only after executing the command with(DeepLearning). However, it can always be accessed through the long form of the command by using DeepLearning[DNNClassifier](..).

Compatibility

 • The DeepLearning[DNNClassifier] command was introduced in Maple 2018.