Towards an absolute measure of change in temperature — The planet is heating up. How much? How fast? In the media, you’ll read that the planet is, on average, about 1° Celsius warmer than a century ago. You’ll also read that the landmasses are getting warmer faster than the oceans. But these are only averages; they miss the details. …

If it looks like a duck… — A few days ago, the Internet was taken by countless tweets, posts, and articles about Google's LaMDA AI being conscious (or sentient) based on a conversation it had with an engineer. If you want, you can read it here. If you read it, you will also realize that it surely…

Seven guiding principles for writing technical posts — One million views! To be honest, I thought this magnitude of viewership was reserved for celebrities only. I cannot even say I had always dreamed about having this many views because I thought such a feat would be forever beyond my reach. But here we are, 4 years later, celebrating…

Part II: Variational AutoEncoders — Introduction Autoencoders are cool, and variational autoencoders are cooler! This is the second (and last) article of the "Understanding AutoEncoders with an example" series. In the first article, we generated a synthetic dataset and built a vanilla autoencoder to reconstruct images of circles.

Part I: Vanilla AutoEncoders — Introduction Autoencoders are cool! They can be used as generative models, or as anomaly detectors, for example. Moreover, the idea behind an autoencoder is actually quite simple: we take two models, one encoder and one decoder, and place a “bottleneck” in the middle of them. Then, we give it the same…

Understanding how the "reverse" convolution works — Introduction Transposed convolutions are like the "ugly duckling" of the convolutional family. They are quirky and weird, but there's more to a transposed convolution than it meets the eye. You will often find layers of transposed convolutions in the decoder part of AutoEncoders, or in the generator part of GANs. Their…

Setting up your experiments in Python, Numpy, and PyTorch — Motivation "What is a programmer's worst nightmare?" On my part, I can safely say that my worst nightmare, as a programmer, is a piece of code that behaves as if it were random, spewing out different results every time I run it, even if I give it the very same inputs! …

Higher-Order Functions and Decorators in Python with Examples — Higher-order functions are an important topic, and I believe you should have a good grasp on how they work to fully benefit from Python’s capabilities and make the best out of your code. I will illustrate higher-order functions with an example so that you can gain a working knowledge of…

As I write these lines, I'm a few days away from releasing the last two chapters of my book, "Deep Learning with PyTorch Step-by-Step: A Beginner's Guide". …