ML Systems in the Real World

This lesson summarizes the guidelines learned from these real-world examples.

Real World Guidelines

Some Effective ML Guidelines

  • Keep the first model simple

Some Effective ML Guidelines

  • Keep the first model simple
  • Focus on ensuring data pipeline correctness

Some Effective ML Guidelines

  • Keep the first model simple
  • Focus on ensuring data pipeline correctness
  • Use a simple, observable metric for training & evaluation

Some Effective ML Guidelines

  • Keep the first model simple
  • Focus on ensuring data pipeline correctness
  • Use a simple, observable metric for training & evaluation
  • Own and monitor your input features

Some Effective ML Guidelines

  • Keep the first model simple
  • Focus on ensuring data pipeline correctness
  • Use a simple, observable metric for training & evaluation
  • Own and monitor your input features
  • Treat your model configuration as code: review it, check it in

Some Effective ML Guidelines

  • Keep the first model simple
  • Focus on ensuring data pipeline correctness
  • Use a simple, observable metric for training & evaluation
  • Own and monitor your input features
  • Treat your model configuration as code: review it, check it in
  • Write down the results of all experiments, especially "failures"

Video Lecture Summary

Here's a quick synopsis of effective ML guidelines:

  • Keep your first model simple.
  • Focus on ensuring data pipeline correctness.
  • Use a simple, observable metric for training & evaluation.
  • Own and monitor your input features.
  • Treat your model configuration as code: review it, check it in.
  • Write down the results of all experiments, especially "failures."

Other Resources

Rules of Machine Learning contains additional guidance.

Send feedback about...

Machine Learning Crash Course