Deep Learning for Computer Vision with SAS. Robert Blanchard

1.2: Comparison of Central Processing Units and Graphical Processing Units

Central Processing Unit (CPU)	Graphical Processing Unit (GPU)
Faster Clock Speed	Slower Clock Speed
Fewer Processing Units	More Processing Units
More Branching	Less Branching
Less Memory Bandwidth	More Memory Bandwidth

      The optimization techniques used to adjust the weights of a neural network are iterative processes. However, within each iteration, the weights are updated simultaneously. Therefore, calculations corresponding to each weight update can be distributed among processing units. GPUs are designed to perform many operations in parallel, which fits nicely with the weight update process used by neural networks.

      The use of GPUs should be reserved for larger neural networks because the difference in performance between CPUs and GPUs is negligible in neural networks with a small number of parameters.

Deep Learning Actions

      As an integrated part of the SAS Platform, SAS Viya is a cloud-enabled, in-memory analytics engine that provides quick, accurate, and reliable analytical insights. SAS Viya offers a rich set of data mining and machine learning capabilities that run on a robust in-memory distributed computing infrastructure that provides a single environment that is unified, open, powerful, and cloud ready.

      The SAS Cloud Analytic Services actions can be surfaced through SAS Viya on a number of interfaces, including SAS Studio and Jupyter notebook.

      This book highlights three of the deep learning actions in SAS Cloud Analytic Services (CAS):

      ● deep feed-forward neural network (DNN)

      ● convolutional neural network (CNN)

      ● recurrent neural network (RNN)

      DNN actions are used to solve more traditional classification problems, such as fraud detection. CNN actions are commonly used to build more advanced neural networks for either traditional or computer vision data problems. An RNN is used to solve problems for data that is some function of a sequence, such as time series or text analyses.

      SAS deep learning actions can be called using several programming languages, including SAS, R, and Python. This book focuses on the use of SAS to call Cloud Analytic Services through the CAS procedure.

      The CAS procedure enables you to interact with SAS Cloud Analytic Services from the SAS client by providing a programming environment based on the CASL language specification. The programming environment enables you to run CAS actions and use the results to prepare the parameters for another action. Code is formatted as

      PROC CAS;<CASL code>Quit;

      An example of this is

      PROC CAS < exc >< noqueue >;BuildModel/ modeltable={name=”<Model table name >”}type=”DNN”;Quit;

      For CNNs and RNNs, replace the type=“DNN” with type=“CNN” and type=“RNN”, respectively.

      The CAS procedure has several features that enable you to perform the following operations:

      ● run any CAS action that is supported by the server, even if the action did not exist at the time of the release

      ● use multiple sessions to perform asynchronous execution