DeepLearning makes use of the following custom types

The core object in a DeepLearning computation is a Tensor. The following commands construct Tensor objects in the active graph.

The following commands allow querying and modification of the DataflowGraph in which the current computation occurs.

The following commands construct Estimator objects for classification and regression tasks.

The following commands construct FeatureColumn objects for use with an Estimator.

The following commands manage Session objects.

The DeepLearning package is implemented using Google TensorFlow™ and provides access to a subset of the TensorFlow Python API, version 2.2.0.

The DeepLearning package is currently not supported on the following platforms: Macs powered by Apple's M1 chip (Apple Silicon).

For Windows, a processor with AVX instructions is required. For more information, see the Release 1.6.0 section in https://github.com/tensorflow/tensorflow/blob/r1.10/RELEASE.md.

The DeepLearning package was introduced in Maple 2018.

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