TensorFlow from the ground up

6 easy pieces on what you need to know for TensorFlow from the ground up (tensors, variables, and gradients without using high level APIs).

This talk is designed for those that know the basics of Machine Learning but need an overview on the fundamentals of TensorFlow.

Chapters:

0:00 – Intro and outline

2:12 – Tensors

6:08 – Variables

9:19 – Gradient tape

13:57 – Modules

17:43 – Training loops

21:52 – tf.function

28:53 – Conclusion

Resources:

This talk is based on the guides on tensorflow.org See them all (with executable code on Google Colab!)

→ https://goo.gle/3ije3k5

Tensors

→ https://goo.gle/34UqV8m

Variables

→ https://goo.gle/3v2Pvyh

Introduction to gradients and automatic differentiation

→ https://goo.gle/3sFVybo

Introduction to graphs

→ https://goo.gle/3w1cGdE

Introduction to modules, layers, and models

→ https://goo.gle/3v0mSC1

Basic training loops

→ https://goo.gle/3uZ9pu0