Skip main navigation

Multilayer Perceptrons

Neural Networks We’re now ready to introduce the concept of a neural network. You probably realise that “neural” means these networks are somehow connected to the human brain. While it’s …

End-to-end autonomous driving

What rules do self-driving cars need in order to naviagate in highly complex real-world road environments? Watch Dr Will Smith explain more.

How do maze-solving robots work?

To plan and navigate a particular environment, you will need a model of that environment. Even if the model of the environment is perfect and free from noise, finding an …

Deep fakes

GANs can synthesise not just random indentities but faces of specific people too. Dr Will Smith explains how. References Kim, Hyeongwoo, et al. “Deep video portraits.” ACM Transactions on Graphics …

What can you do with GANs?

Here, we give you some GAN results and give examples of some of the things we can do with a GAN. Random face synthesis Once a GAN is trained, we …

How do GANs generate faces?

Here, we look at how the concept of an adversary can be turned to our advantage. We are going to focus on the task of generating random, photorealistic images of …

What is an adversarial example?

Here we’re going to look at a weakness of neural networks – a way that they can be ‘attacked” by an adversary in order to produce nonsensical output. Adversarial examples …

Backpropagation and SGD

We have seen that, if we can compute the gradient of the loss function with respect to the parameters (weights and biases) of our MLP, we can perform gradient descent …

An introduction to safety assurance and ethics

Computer-controlled cars are almost here. Many production cars now include software features to assist human drivers. Dr Jenn Chubb talks about the safety assurance and ethics issues that we face.

Face recognition in humans

Humans have a remarkable ability to interpret the visual appearance of a face. Dr Will Smith explains how we have evolved this extraordinary ability.

Deep face recognition

The problem of face recognition usually takes one of two possible forms: “Am I who I say I am?” – This is known as face authentication. A user presents an …

Deep learning wrap-up

We’ve now covered enough of the basics to be able to do some amazing things with deep learning. CNNs (such as the VGG architecture) trained with stochastic gradient descent using …

What are Convolutional Neural Networks?

A Convolutional Neural Network (ConvNet / CNN) is a Deep Learning algorithm which, when given an input image, can assign value or importance to various aspects or objects in the …

Deep learning on images

An image is simply a rectangular array of pixels. Dr Kofi Appiah explains how we can process and understand that data.

What is Computer Vision?

What is Computer Vision and Why is it Useful? Extracting useful information from images or seeking to understand images using computers is called computer vision. This is a very broad …