Introduction to Machine Learning

Machine Learning is incredibly exciting and it’s not just science fiction. This 5-class series is a practical, hands-on dive into machine learning, after which you will be ready to deliver immediate value to any organization. You will learn by doing, and create, optimize and debug your own models. Your time is precious - our classes are fast-paced and cover as much material as possible.

Don't just take our word for it - this is how students describe our classes:

"It was great to have all the code in Github and in multiple files, each showing a new step covered, so we could follow along.”
"The classes are excellent; I now have a solid foundation with which I can navigate trying machine learning techniques to solve my issues"
"The class is very well organized and the resources provided were top-notch."

Getting Started

All of the content for these videos is conveniently stored in a Github repository which you can download. We highly recommend following along and tweaking the code for yourself. See more instructions on getting started here.

What is machine learning?

What is the difference between AI, Machine Learning and Deep Learning? Why does machine learning matter? What can it do, and perhaps more importantly, what can’t it do? Get started by looking at your first machine learning model and learning about multivariate linear regression, overfitting, loss functions and the machine learning API.

Build your first neural network

In this class, you will build a simple neural network to classify handwritten digits into “five” or “not five”. You will learn the basics of machine learning, Keras, gradient descent, loss functions, weighting, and how to tweak hyperparameters.

Multiclass and Multilayer Perceptrons

We expand our neural network to a multiclass perceptron to classify all numbers 0-9, and a multi-layer perceptron to increase accuracy. You will learn about one-hot encoding, activation functions, dropout, data normalization and categorical cross entropy.

Convolutional Neural Networks

In this class, you will create a convolutional neural network that works with images. You will learn about convolutions, pooling, and feeding in images to the machine learning API.


Autoencoders are a really cool application of neural nets, and a great place to start if you want to learn more about generative adversarial networks (GANs). They are used to compress information, generate synthetic images and remove noise from images. In this class we will walk you through how to create, optimize and debug your own autoencoder.

Sentiment Analysis

In this class, you will build a model that classifies tweets about a brand as having either a positive or negative sentiment, and extract the topic of the tweet. You will use the scikit learn library and learn about data processing, feature extraction and choosing a text classification algorithm.