Machine Learning

This workshop introduces students to scikit-learn, the popular machine learning library in Python, as well as the auto-ML library built on top of scikit-learn, TPOT. The focus will be on scikit-learn syntax and available tools to apply machine learning algorithms to datasets. No theory instruction will be provided.

Machine learning often evokes images of Skynet, self-driving cars, and computerized homes. However, these ideas are less science fiction as they are tangible phenomena that are predicated on description, classification, prediction, and pattern recognition in data. During this two part workshop, we will discuss basic features of supervised machine learning algorithms including k-nearest neighbor, linear regression, decision tree, random forest, boosting, and ensembling using the tidymodels framework. To social scientists, such methods might be critical for investigating evolutionary relationships, global health patterns, voter turnout in local elections, or individual psychological diagnoses.

The goal of this workshop is to build intuition for deep learning by building, training, and testing models in Python. Rather than a theory-centered approach, we will evaluate deep learning models through empirical results.

This workshop presents a brief history of Artificial Neural Networks (ANNs) and an explanation of the intuition behind them; a step-by-step reconstruction of a very basic ANN, and then how to use the scikit-learn library to implement an ANN for solving a classification problem.