Have you heard people talking about machine learning but only have a fuzzy idea of what that means? Are you tired of nodding your way through conversations with co-workers? Let’s change that!
This guide is for anyone who is curious about machine learning but has no idea where to start.

Learn how about neural networks and how recurrent neural networks can be used to general new data based on existing data.

Learn how Convolutional Neural Networks work and how they are used to recognize objects in photographs.

Let’s learn how modern face recognition works! But just recognizing your friends would be too easy. We can push this tech to the limit to solve a more challenging problem — telling Will Ferrell (famous actor) apart from Chad Smith (famous rock musician)!

Sequence-to-sequence learning is a very powerful technique that revolutionizing language translation. After we see how it is used for translation, we’ll also learn how the exact same algorithm can be used to write AI chat bots and describe pictures.

But speech recognition has been around for decades, so why is it just now hitting the mainstream? The reason is that deep learning finally made speech recognition accurate enough to be useful outside of carefully controlled environments. Let’s learn how to do speech recognition with deep learning!

Deep Convolutional Generative Adversarial Networks (or DCGANs for short) are one of the most exciting new areas of machine learning research. DCGANs are able to hallucinate original photo-realistic pictures by using a clever combination of two deep neural networks that compete with each other. Let’s use generative models to do something a bit more silly — make artwork for 8-bit video games!

Automatically scrape data out of web pages with one line of code!

To make it simple for anyone to play around with machine learning, I’ve put together a simple virtual machine image that you can download and run without any complicated installation steps.

One common complaint about the Python language is that variables are Dynamically Typed. That means you declare variables without giving them a specific data type. But with Python 3.6, you now have the choice of using Static Type Checking which can automatically catch many common errors while coding!

If you have a computer made in the last decade, there’s a good chance it has 4 (or more) CPU cores. That means that 75% or more of your computer’s power is sitting there nearly idle while you are waiting for your program to finish running! Let’s learn how to take advantage of the full processing power of your computer by running Python functions in parallel.

Almost as long as programmers have been writing computer programs, computer hackers have been figuring out ways to exploit those programs. Malicious hackers take advantage of the tiniest bugs in programs to break into systems, steal data and generally wreak havoc.

Everyone hates CAPTCHAs — those annoying images that contain text you have to type in before you can access a website. Let’s hack the world’s most popular Wordpress CAPTCHA Plug-in with machine learning!

One of programming’s little annoyances is that Microsoft Windows uses a backslash character between folder names while almost every other computer uses a forward slash. But pathlib makes it easy to deal with this.

Need to extract data from plain text? Learn how to build an NLP Pipeline in Python!

Sometimes the most complicated solution isn’t the best. Learn the tricks that real companies used to quickly parse messy text from social media posts and user-contributed content.

Sometimes having a model that works but not knowing how it works isn’t good enough. But thanks to new techniques like LIME, we now have ways to see inside the black box. Let’s learn how to understand what our models are thinking!

Build a high-accuracy parking space notification system with Python and Deep Learning!

Let's walk through setting up a Jetson Nano and using it to build a doorbell camera that can track everyone who walks up to your house using face recognition.

How easy it is for an average person to generate fake news that could trick a real person and how good are the results?

Let’s explore how a system like this could work and how much of a threat it is. Let’s try to build a newspaper populated with fake, computer generated news!

In my experience, there is one technical problem that trips people up more often than any other. No, it’s not a complicated theoretical issue or an issue with expensive GPUs. It’s the fact that almost everyone is loading their images into memory sideways without even knowing it.