Live-coding a machine learning model from scratch

Video description

Do you want to build a machine learning model, but you aren’t sure where to start? Starting with an empty notebook, Sara Robinson (Google) live-codes a simple neural network in TensorFlow. She then demonstrates how to train and serve the model on Google Cloud Platform and uses the deployed model to generate predictions from a web app.

Prerequisite knowledge

  • A basic knowledge of Python and machine learning concepts, such as training and serving (but not necessarily how to build a model on your own)

What you'll learn

  • Learn how to build a simple neural network
  • Understand the end-to-end ML workflow and how to use your trained model for generating predictions

This session was recorded at the 2019 O'Reilly Open Source Software conference in Portland.

Product information

  • Title: Live-coding a machine learning model from scratch
  • Author(s): Sara Robinson
  • Release date: December 2019
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 0636920335818