This 11-video course explores the concepts of computational graphics, interfaces for programming graphics processing units (GPUs), and TensorFlow Extended and its pipeline components. Learners discover features and elements that should be considered for machine learning when building deep learning (DL) models, as well as hyperparameters that can be tuned to optimize DL models. Begin by examining the concept of computational graphs and recognize essential computational graph operations used in implementing DL. Then learn to list prominent processors with specialized purpose and architectures used in implementing DL. Recall prominent interfaces for programming GPUs with focus on Compute Unified Device Architecture (CUDA) and OpenCL, and then take a look at TensorFlow Extended (TFX) and TFX pipeline components for machine learning pipelines. Discover how to setup the TFX environment; use the ExampleGen and StatisticsGen TFX pipeline components to build pipelines; work with TensorFlow Model analysis; and explore the practical considerations for DL build and train. Finally, recall essential hyperparameters of DL algorithms that can be tuned to optimize DL models. The concluding exercise involves optimizing DL applications.

Implementing Deep Learning: Optimized Deep Learning Applications

discover the key concepts covered in this course

define the concept of computational graphs and recognize the essential computational graph operations that are used in implementing deep learning

list the prominent processors with specialized purpose and architectures that are used in implementing deep learning

recall the prominent interfaces for programming GPUs with focus on CUDA and OpenCL

define the concept of TensorFlow Extended and list the essential TFX pipeline components that can be used to implement machine learning pipelines

setup the TensorFlow Extended environment to build deep learning pipelines

demonstrate how to use the ExampleGen and StatisticsGen TFX pipeline components to build pipelines

work with TensorFlow Model Analysis to investigate and visualize the characteristics of datasets and the performances of models

recognize the practical features and elements that should be considered when building deep learning models, with focus on baseline model and optimization

recall the essential hyperparameters of deep learning algorithms that can be tuned to optimize deep learning models

identify components of a computation graph, common GPU frameworks, and tasks that can improve performance with data