How to Generate Images – Intro to Deep Learning

We’re going to build a variational autoencoder capable of generating novel images after being trained on a collection of images. We’ll be using handwritten digit images as training data. Then we’ll both generate new digits and plot out the learned embeddings. And I introduce Bayesian theory for the first time in this series 🙂

Code for this video:…

Mike’s Winning Code:…

SG’s Runner up Code:…

Please subscribe! And like. And comment. That’s what keeps me going.

2 things
-The embedding visualization at the end would be more spread out if i trained it for more epochs (50 is recommended) but i just used 5.
-The code in the video doesn’t fully implement the reparameterization trick (to save space) but check the GitHub repo for details on that.

More Learning resources:………………

Join us in the Wizards Slack channel:

And please support me on Patreon:


Amazon Echo having a conversation with Google Home

Let your Amazon Echo (Alexa) have a conversation with Google Home!

For those who are interested in the technical aspects:

By saying ‘Echo, start small talk”, a custom app for the Echo (called ‘skill’) is invoked and the Echo starts the conversation. On Google Home, there isn’t running any custom app at any time.

Every time the Echo asks Google Home a question, it waits for its answer and (when it asks for the time) later processes the input.

After the last command has been spoken by the Echo, the skill stops. When Google Home responds with ‘Echo, you are great!’, the base functionality of Amazon Echo gets invoked (not a custom skill).

The skill is not published.

Here’s another video demonstrating some different functionality – shot in the dark: