The Real-World ML Tutorial

Source: https://realworldmachinelearning.carrd.co/

Hello! I am Pau, a machine learning engineer with many years of experience in developing real ML products. Would you like to design, develop, and implement your own ML product?

This course will show you how to create fully functional ML solutions from concept to production, helping startups and large companies solve business challenges.

What awaits you inside:

• From business to ML
  • Learn to translate a business problem into an ML task.
  • Master four key steps: from raw data to a full-fledged ML solution, not just a simple prototype.
  • Data preparation
  • Learn how to transform raw data into ready features and target variables.
  • Create a reliable data pipeline in Python: collection, validation, transformation, and generation of training data.
• Model prototyping
  • Learn to quickly create and improve basic models.
  • Step by step, enhance them using feature engineering and boosting.
  • Master hyperparameter optimization to get the most out of the data.
• Deploying and monitoring the model
  • Turn a prototype into a working batch-scoring system using Feature Store and CI/CD.
  • Create a dashboard to display “live” forecasts.
  • Set up a system for monitoring the quality and stability of the model.

Who is this course for?

• For those who can already prepare data and train models in a notebook but don’t know how to turn them into a working service.
• For specialists who want to learn how to design, implement, and deploy a real ML solution from start to finish.
• For those who aspire to get a job as an ML engineer and want to master the practice of building complete ML systems.

What will you get:

• hours of video lectures and presentations, regularly updated.
• Full source code in a GitHub repository.

What will you build:

• In the course, you will create a complete ML service that forecasts taxi demand in New York. The methods and tools you will master (pipelines, MLOps, monitoring, etc.) are applicable in any industry.

Password: cms.ddpanda.org