Automated language identification: A common machine learning task is to identify the language of a written text sample. This lab introduces and evaluates the method of cosine similarity as a solution to this task. Image: Conor O’Sullivan.

Cosine similarity and large language models: Cosine similarity, introduced in the language lab, also appears in large language model embedding layers.

Data sets and feature vectors: An introduction to a few standard machine learning data sets and ways to format the data using feature vectors.

Clustering and classification: A brief overview of one of the fundamental problems in machine learning. How should similarity be measured to produce clusters or groups among feature vectors?

Regression: A collection of labs and exercises introducing data models, regression, and methods of evaluating the quality of predictions made by them.

Neural networks: A collection of labs and activities introducing neural networks in the context of multivariable calculus.