From the course: Building and Deploying Deep Learning Applications with TensorFlow
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Why is it called TensorFlow? - TensorFlow Tutorial
From the course: Building and Deploying Deep Learning Applications with TensorFlow
Why is it called TensorFlow?
- [Teacher] Alright, what's with the name? The name TensorFlow comes from the design of the system. TensorFlow is designed to work with large data sets made up of many different individual attributes. Any data that you want to process with TensorFlow has to be stored in the multi-dimensional array. These multi-dimensional arrays are also called tensors. To run operations on the data set, you construct a computational graph similar to a flow chart that determines how data flows from one operation to the next. So it's called TensorFlow because you're defining how data or tensors will flow through the system. Here, we are passing in two tensors, adding those numbers, squaring them and then outputting the result as another tensor. TensorFlow is designed to be very generic and open-ended. You can define the graph of operations that does any calculation that you want. While TensorFlow is most often used to build deep neural networks, it can be used to build nearly anything that involves…
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.