This site contains a series of lessons to each non-computing people about machine learning (ML). The lessons are all in Jupyter Notebook form, and are intended to run in Google’s Colaboratory environment. Working through these lessons will not make you an expert in the field, but will give you enough of an introduction to get started with your own projects.

The current lessons are:

1. Machine learning introduction
2. School attendance rates regression
3. Iris classification
4. Breast cancer tumor classification

New content will be added periodically, and each new addition will be accompanied by a new blog post.

Blog posts

• Breast Cancer Tumor Classification

  Is it cancer?

  Posted on October 12, 2023

  Our third lesson is another classification problem. In the lesson, we will train a computer to be able to tell us whether or not a mass is likely to be cancerous, based on a variety of measurements of the mass. The dataset is found here. In this classification problem, we... [Read More]

  Tags:

  • classification

• Machine Learning (Introduction)

  Want your computer to learn? Start here!

  Posted on October 11, 2023

  Machine learning is a type of artificial intelligence, where we somehow make a computer learn how to solve a problem, without having to explicitly program the machine to solve the problem. In other words, the computer learns how to solve a problem that we could not otherwise develop a program... [Read More]

  Tags:

  • classification
  • regression

• Iris Classification

  Which flower is it, *precisely*?

  Posted on October 11, 2023

  Our second lesson is a classification problem. In the lesson, we will train a computer to be able to tell us what species an iris is, based on measurements of its petal length and width. The example uses a famous dataset created by Sir R. A. Fisher in 1936. This... [Read More]

  Tags:

  • classification

• Attendance Rates Regression

  How many students will show up?

  Posted on October 11, 2023

  Our first lesson is a regression problem, where we try to predict the attendance rate for a school, based on a variety of input variables. The data we use here is open data from the public school districts in Connecticut, obtained from the data.gov stie. This example uses what is... [Read More]

  Tags:

  • regression