Target Audience:
- Newer and intermediate programmers with some basic CS background and familiarity with programming
Suggested Prerequisites:
- Python (or another Object Oriented Language)
Workshop Goals:
- Understand how to create a supervised machine learning model end-to-end
- Learn to pre-process and clean data
- Learn to load in new data from various format for creating a new model
Description:
Machine Learning (ML) can often seem intimidating, or like you would need a strong background in statistics/math, but that simply is not true. Applied machine learning focuses on the implementation side of ML breakthroughs, and relies heavily on a developer's critical thinking skills.
This session will explore using the ML project pipeline, Microsoft Azure (Jupyter) Notebooks, scikit-Learn, and other industry standard Python based ML libraries for developing a simple ML project from start to finish. Absolutely no ML or Python experience is needed (although you should have a little coding).
Content Breakdown:
- Intro to ML Concepts
- The basic theory and ideas of machine learning, and explaining different subsets of the field.
- Machine Learning Project Flow
- Covering the steps in completing a machine learning project.
- End-to-End Solution in Python
- An interactive code walkthrough of an end-to-end machine learning project.