This online course provides a theoretical and practical guide to the use of face-swap technology. In the past few months, deep neural networks have been wildly used to digital insert actor Nicolas Cage into several movie scenes. These so-called deepfakes have generated a lot of discussion on the ethics of Machine Learning. This second lesson will focus on the potential applications that face-swap technology can offer, and on how to use it properly.
If you are interested in understanding not only how deekfakes are generated, but also to create your own, this is the tutorial you have been looking for. And if you have been using face-swap technology already, I hope this first post will help you become more aware of why and how this technology should (and shouldn’t) be used.
This tutorial will cover the theory and practice of creating deepfakes: videos in which faces have been swapped using Machine Learning and Deep Neural Networks. If you are interested in learning more about this novel technique, this is the course for you.
After a theoretical introduction, this course will focus on how to make the most out of the popular applications FakeApp and faceswap; most of the deepfakes you will find online (such as the ones featuring Nicolas Cage) have been created using them.
This post shows how it is possible to find the position of an object in space, using a technique called trilateration. The traditional approach to this problem relies on three measurements only. This tutorial addresses how to it is possible to take into account more measurements to improve the precision of the final result. This algorithm is robust and can work even with inaccurate measurements.
This series introduces the concept of trilateration. This technique can be applied to a wide range of problems, from indoor localisation to earthquake detection. This first post provides a general introduction to the concept of geographical coordinates, and how they can be effectively manipulated. The second post in the series, Positioning and Trilateration, will cover the actual techniques used to identify the position of an object given independent distance readings. Most trilateration tutorials require the measures from the sensors to be precise and consistent. The approach here presented, instead, is highly robust and can tolerate inaccurate readings.
The previous post in this series, Understanding Deep Dreams, explained what deep dreams are, and what they can be used for. In this second post you’ll learn how to create them, with a step by step guide.