A feature column is a high-level representation of a feature, used by Estimator models such as DNNClassifier.

A feature is any measurable property of the input data, such as a numerical or categorical data.

DeepLearning offers several types of feature columns.

$\mathrm{with}\left(\mathrm{DeepLearning}\right)\:$

$\mathrm{fc}≔\mathrm{NumericColumn}\left(''SepalLength''\,\mathrm{shape}=\left[1\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$\mathrm{fc}≔\left[\begin{array}{c}\mathrm{Feature\; Column}\\ \mathrm{NumericColumn(key=\text{'}SepalLength\text{'},\; shape=(1,),\; default\_value=None,\; dtype=tf.float64,\; normalizer\_fn=None)}\end{array}\right]$

The DeepLearning[FeatureColumn] command was introduced in Maple 2018.

For more information on Maple 2018 changes, see Updates in Maple 2018.