
Abstract: Thanks to packages like Keras and Torch, you can get started with neural networks with only a few lines of R code. Once you understand the basic concepts, you will be able to use deep learning to make AI-generated humorous content! In this workshop you'll get to make a neural network on text data to generate pet names. By the end of the workshop you should feel comfortable using neural networks in a variety of contexts.
Session Outline
Overview - a quick introduction to what neural networks are and the history of them in R
The first neural network - making a Keras LSTM neural network based on the example data
Using the model - how to take the neural network that was trained and use it
Designing complex networks - changing the network type to use different layers like convolutions
Bio: Dr. Jacqueline Nolis is a data science leader with 15 years of experience in running data science teams and projects at companies ranging from Airbnb to Boeing. She is the Head of Data Science at Saturn Cloud where she helps design products for data scientists. Jacqueline has a PhD in Industrial Engineering and her academic research focused on optimization under uncertainty. For fun Jacqueline likes to use data science for humor—like using deep learning to generate offensive license plates.

Dr. Jacqueline Nolis
Title
Head of Data Science | Saturn Cloud
