Machine learning and artificial intelligence
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 covering 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, with a look at neural networks. 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 (normally 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 in order 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 be used to generate “deepfakes” to fool people, and what that means for trust.
You’ll also look at alternatives to deep learning; you’ll compare their strengths and weaknesses to the deep learning systems you’ve seen. Part of the differences 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; to 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:
You may enrol on TM358 while still studying M269. However, if you do not pass M269, we must cancel your enrolment on TM358.
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.
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
- assignment details and submission section
- an online computing environment for practical work
- online tutorial access.
Computing requirements
You’ll need broadband internet access and a desktop or laptop computer with an up-to-date version of Windows (10 or 11) or macOS Ventura or higher.
Any additional software will be provided or is generally freely available.
To join in spoken conversations in tutorials, we recommend a wired headset (headphones/earphones with a built-in microphone).
Our module websites comply with web standards, and any modern browser is suitable for most activities.
Our OU Study mobile app will operate on all current, supported versions of Android and iOS. It’s not available on Kindle.
It’s also possible to access some module materials on a mobile phone, tablet device or Chromebook. However, as you may be asked to install additional software or use certain applications, you’ll also require a desktop or laptop, as described above.