Machine learning has blown up in popularity in the past decade, with applications from healthcare to self-driving cars, being used to create art, play video games, and act as customer service representatives. One of the most common and useful tools for these applications are neural networks: universal function approximators. This interactive workshop is meant for people with little or no machine learning experience, and is split into three parts: classification, convolutions, and autoencoders, and will cover all of the necessary mathematical background to get your first neural networks up and running. We will be using the popular MNIST dataset as a starting point for your own future research with machine learning tools. Consider this an ad for Dr. Flores and Dr. Tran’s Applications of Machine Learning class in the Fall.

No experience with AI is required, but it helps if you’ve used Python before, and a background in calculus and linear algebra is helpful.

Organizer: Contact A. Colunga for zoom link