AI to Production and Its Pitfalls

Key Takeaways

During the workshop, we will learn how to maintain a machine learning project end to end. We will show you common problems we have seen when deploying machine learning applications,
like:

• Shipping models consistently to production
• Not ensuring data sanity upon requests
• Tracking inputs and outputs to our model
• Input value shift over time
• Previously unknown categories

The workshop will be run in a provided AWS environment. This allows us to work with no prior setup of your local machines. We will anyhow give you all the tools and guides to set it up locally, so you can apply all the knowledge later in whatever environment you have available.

SPEAKER