From the course: TensorFlow: Practical Skills in Constructing, Training, and Optimizing Models
Join today to access over 25,500 courses taught by industry experts.
Understand TensorFlow's core concepts - TensorFlow Tutorial
From the course: TensorFlow: Practical Skills in Constructing, Training, and Optimizing Models
Understand TensorFlow's core concepts
- [Instructor] Grasping the basic building blocks of TensorFlow is crucial for any machine learning project. After this lesson, you'll be able to recognize the key concepts such as tensors, operations, graphs, and sessions in TensorFlow. I'll start with tensors. A tensor is a multidimensional array and it is a primary abstraction in TensorFlow. Most of the objects that you manipulate in TensorFlow will be tensors, and indeed the manipulations themselves will in general simply map tensors to other tensors. Operations are simply the various manipulations we apply to tensors. Sometimes will adjust the dimensions of our tensors or add tensors together. Taken together, tensors and operations compose the bulk of the stuff in TensorFlow. Most of what you do in TensorFlow will be a matter of applying operations to tensors. I'll say a word now about variables. A variable is how we keep track of persisting states in TensorFlow. When we have values that need to be referenced over time, and in…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.