Introduction to Deep Learning Bootcamp

The class is aimed at the curious practitioner, and focuses 70% of its attention on intuition and 30% on application. The class is geared to not only show you the tools to get your deep machine learning models off the ground quickly, but to show you the right way to use them and what is going on behind the scenes of these black box models. By the end of the class you’ll be able to solve problems as simple as predicting housing prices up to problems as complex as facial recognition.

We will build strong intuitions for important deep learning concepts ranging from Multi Layer Perceptrons to Convolutional Neural Networks (don’t worry if you don’t yet know these terms!). We will work with the popular tensorflow and keras libraries to quickly build and visualize deep learning models. And we will visualize everything we can along the way — from the way the model learns to separate data to the internal representations.

The class will not be mathy (no calculus), but will require a bit of coding to get the most out of it.

Takeaways

• Understand important deep learning ideas from the ground up, e.g. Multi Layer Perceptrons & Convolutional Neural Networks
• Apply these ideas by effectively using the popular deep learning libraries Tensorflow and Keras
• Know when and how to open the “black box” that is a Neural Network to peek inside and understand what is happening

Prereqs & Preparation
Students are expected to be familiar with python (Intro to Python Bootcamp), and a basic understanding of Machine Learning (i.e. know how to run a linear regression) would be helpful. Any prior knowledge in Deep Learning is a plus, but an interest is a must!