Computers are getting smarter. Intelligent assistants like Alexa and Siri, image searches that find the topic of a photo, and self-driving cars – these intelligent systems use machine learning to develop their expertise. In this module, you’ll learn about various machine learning techniques but concentrate on deep neural learning. You’ll learn about the underlying theory and get hands-on experience creating, training, evaluating, and using machine learning systems. You’ll also examine how these technologies are used and misused and what that means for our societies and communities.
What you will study
The module is divided into several blocks. Each covers a different aspect of machine learning.
You’ll start with an introduction that outlines some of the issues surrounding machine learning, including questions about how machine learning systems are used and their social effects.
Deep neural learning is introduced, and neural networks are examined. You’ll create, train, and evaluate some neural networks to perform tasks such as handwriting recognition. You’ll also see how these networks don’t scale up to larger problems.
Convolutional neural networks solve many of these problems. You’ll learn how these networks start by identifying small features in their inputs (typically images). Successive layers in the inputs combine these features into larger ones, eventually leading to a classification in the image.
Recurrent neural networks operate on time-dependent data, such as language. You’ll learn how they retain information seen earlier to interpret what’s happening now. You’ll use them to understand and generate some text.
Autoencoders teach themselves to compress and reconstruct their inputs. You’ll see how to use this for both compression and to clean data and replace missing data. You’ll see how this can generate “deepfakes” to fool people, and what that means for trust.
You’ll also look at alternatives to deep learning and compare their strengths and weaknesses to the deep learning systems you’ve seen. Part of the difference lies in how the data should be prepared for different systems. As well as the time needed, preparation is another way for bias to creep into the system.
The conclusion asks you to review the technical aspects of machine learning, consider how these systems are used, and the effects this could have on individuals and society.
Entry requirements
To begin TM358, you must have passed the following module:
Algorithms, data structures and computability (M269).
Preparatory work
Key topics to revise include:
data structures in Python, such as lists, dicts, and combinations of them
control structures such as loops and conditionals
decomposition of programs into procedures.
Teaching and assessment
Support from your tutor
You’ll get help and support from an assigned tutor throughout your module.
They’ll help by:
marking your assignments and offering detailed feedback to help you improve
providing individual guidance, whether that’s for general study skills or specific module content
guiding you to additional learning resources
facilitating online discussions between your fellow students in the dedicated forums.
Online tutorials run throughout the module. While they’re not compulsory, we strongly encourage you to participate. Where possible, we’ll make recordings available.
Assessment
Course work includes:
3 Tutor-marked assignments (TMAs)
End-of-module assessment
What's included
You’ll have access to a module website, which includes:
a week-by-week study planner
course-specific module materials
audio and video content
assessment details and submission section
online tutorial access
access to student forums.
Computing requirements
Primary device – A desktop or laptop computer with at least 8 GB of RAM and a quad-core processor (2.4 GHz minimum speed). It’s possible to access some materials on a mobile phone, tablet or Chromebook; however, they will not be suitable as your primary device.
Peripheral device – Headphones/earphones with a built-in microphone for online tutorials.
Operating systems – Windows 11 or the latest supported macOS.
Internet access – Broadband or mobile connection.
Browser – Google Chrome and Microsoft Edge are recommended; Mozilla Firefox and Safari may be suitable.
Our OU Study app operates on supported versions of Android and iOS.
Software – Any additional software will be provided or is generally available for free.
If you have a disability
The OU strives to make all aspects of study accessible to everyone, and this Accessibility Statement outlines what studying TM358 involves. You should use this information to inform your study preparations and any discussions with us about how we can meet your needs.
To find out more about what kind of support and adjustments might be available, contact us or visit our Disability support website.
Future availability
Machine learning and artificial intelligence (TM358) starts once a year – in October.
It will next start in October 2027.
We expect it to start for the last time in October 2029.