Course Description
Explore the concept of machine learning in TensorFlow, including TensorFlow installation and configuration, the use of the TensorFlow computation graph, and working with building blocks.
Learning Objectives
TensorFlow: Introduction to Machine Learning
- Course Overview
- describe kinds of machine learning algorithms and their use cases
- define the training and prediction phases in machine learning
- define the conceptual differences between traditional machine learning and deep learning
- compare and contrast supervised and unsupervised techniques in machine learning
- define the advantages and challenges in using TensorFlow for machine learning
- distinguish data and computations as distinct building blocks of a TensorFlow computation graph
- choose the right way to install TensorFlow based on the user's environment
- install TensorFlow and work with Jupyter Notebooks
- specify constants and build and run a computation graph
- use TensorBoard to visualize the computation graph
- build and execute a computation graph with variables and placeholders
- visualize variables and placeholders on TensorBoard
- recognize how variables are trainable parameters and can be updated within a session
- work with feed dictionaries to input data to placeholders during training
- use named scopes to group computations
- specify and work with eager execution for prototyping and development
- recall basic concepts of machine learning and TensorFlow
- build and execute computation graphs with computation nodes and data