Classification versus regression
So far, we’ve seen how MLPs can be used for parametric machine learning. The MLP outputs one or more values, we give this to a loss function and we use …
Course: Intelligent Systems: An Introduction to Deep Learning and Autonomous Systems
What is Gradient Descent?
Gradient Descent is an optimising algorithm used in Deep Learning algorithms. The goal of Gradient Descent is to minimise the objective convex function f(x) using iteration. It’s time to get …
Optimisation and gradient descent
Optimising loss functions is the key to machine learning. A simple optimisation algorithm is gradient descent. Watch Dr Jenn Chubb explain more.
Machine Learning Data Sets
“Data is the new oil. / Like oil, data is valuable, but if unrefined it cannot really be used.” – Clive Humby (Mathematician) / Michael Palmer (Advertiser) Data and Machine …
Who’s to blame?
Content Warning: At the beginning of this article, there is a short factual description of a fatal accident involving an autonomous vehicle. The remainder of the article explores contributory factors …
Edge cases
The real world is really complicated and sometimes predicting what could happen is almost impossible. Dr Katrina Attwood considers the problems.
Generalisation, bias and overfitting
A machine learning system uses training data to learn a function that maps inputs to outputs. But will the system produce sensible output when presented with input it has never …
What is a machine learning model?
What is a machine learning model? A machine learning model is a program or a file that applies statistical/mathematical techniques in order to recognise certain types of patterns present in …
Ethics by Design
Self-driving vehicles clearly have the potential to produce both benefit and harm to individuals in society. In order to reach useful conclusions about these kinds of questions, it is important …
An introduction to Safety Engineering
What is safety engineering? Safety is about avoiding harm that results from accidents. In order to do that, we need to think about how accidents can be caused, and avoid …
Scene perception in autonomous driving
Is camera data enough to navigate the highly complex real-world road environments safely? Dr Kofi Appiah discusses what other technology is needed.
Sensors for Autonomous Vehicles
We have discussed several sensors that can be added to image sensors to make our autonomous vehicles safer and more reliable. We can look at some of the sensors, their …
Sensor Fusion
Elements like perception, localisation, planning, and control are necessary for the success of any autonomous vehicle. Autonomous vehicles make use of a suite of sensors to collect data from its …
Optimal Route Planning
Determining optimal routes in road networks from a given source to a given target location is a problem frequently addressed in everyday life. Typically, frames from a video camera are …
Deep Learning History
As machine learning engineers, part of our job is to decide on the form of the function that maps inputs to outputs. We’re going to take a brief historical look …
These articles are from the online course:
Intelligent Systems: An Introduction to Deep Learning and Autonomous Systems
