Learning in TensorFlow Seminar

Why should I take this seminar?

This seminar allows you to gain hands-on using TensorFlow and keras to create a machine learning algorithm. This seminar focuses on the steps that you need to perform to create a machine learning algorithm while treating the statistics used to create the algorithms as a black box.

For this and other seminars, the programming language used is Python. We will use TensorFlow, keras, and a couple of other packages.


After completing this seminar, you should be able to:

  1. Describe the data structures used in machine learning
  2. Define basic machine learning concepts
  3. Interpret a program to classify hand-written numbers.

Seminar structure

This seminar has three parts. To earn a digital badge, you need to do all three parts: pre-seminar, live seminar, and post-seminar.

You can complete some parts of the seminar, only the live seminar, or only do the pre- or post-seminar, but to earn a digital badge you must complete all three parts.

Seminar description

During the live seminar you should be able to interpret a basic program in Jupyter notebooks that:

  1. loads the MNIST dataset
  2. explores the MNIST dataset
  3. prepares the MNIST dataset
  4. creates a machine learning model to classify hand-written digits
  5. reports the accuracy of the model

Seminar materials

The pre-seminar module contains:

  1. A note on machine learning (beta version)
  2. Links to resources that describe the history of TensorFlow and keras
  3. A note on using Google Colaboratory

The live seminar module contains:

  1. A pdf of the presentation
  2. Link to try Google's cloud vision API
  3. A page titled Let's try computer vision with images
  4. Jupyter notebook
    1. Jupyter notebook with TensorFlow in Google colaboratory (Hello world of course).
    2. Handwritten digits recognition (the classic machine learning program for beginners).
  5. Links to web resources (TensorFlow, Keras, and Moments in time)

The post-seminar module contains:

  1. A Jupyter notebook with a machine learning algorithm
  2. The annotated Jupyter notebook
  3. Practice test
  4. Final test to earn your digital badge