Artificial Intelligence and Machine Learning: Theory and Practice

In our age of burgeoning smart technology and automation we are already seeing the transformative potential of Artificial Intelligence and Machine Learning in fields as diverse as finance, medicine, and manufacturing. This course offers a hands-on introduction to this future-focused area of research.

You will begin with an introduction to the basics of programming in Python, in particular understanding object-oriented programming and its importance to deep learning. You will quickly proceed to an introduction to artificial intelligence, examining the fundamentals of supervised machine learning, including linear regression, logistic regression, neural networks, and gradient descent. In the second week of the course you will explore image processing, investigating transformations, convolutional filters, and edge detection, before an introduction to convolutional neural networks and some prominent CNN architectures such as VGG and ResNet. In the final part of the course, you will look at the core concepts of natural language processing, including sequence modeling, autoregressive models, and recurrent neural networks.

This intensive course offers both a theoretical introduction to artificial intelligence and machine learning concepts, and an opportunity to put this knowledge into action in solving small-scale practical problems from diverse domains.
 

By the end of this course, you will:

• Understand theoretical concepts of artificial intelligence and machine learning.
• Know how basic artificial intelligence and machine learning tools are used in practice.
• Know how to implement basic algorithms and train small networks for practical problems.
• Be able to identify and use relevant artificial intelligence and machine learning tools in research.
• Know how to implement and deploy artificial intelligence and machine learning algorithms on Google Cloud.

This course would suit STEM students in undergraduate or entry-level postgraduate study. Basic knowledge of calculus and linear algebra is required, and some experience of coding is recommended. Prior experience of artificial intelligence, machine learning, or the Python programming language is not required.

Specifically, basic knowledge includes:

• Basics of Calculus: Multivariate functions, understanding of derivatives and partial derivatives, and the chain rule.
• Basics of Statistics: Probability distributions and fundamental probability theory.
• Basics of Linear Algebra: Vectors, matrices, and solving systems of equations using matrices.
• Optimization: Finding maxima and minima of single-variable and multivariable functions.

Dr Khan is an Instructional Assistant Professor in AI at KAUST, where he is part of the KAUST Academy, the continual learning arm of the university. He is also an Associate Research Fellow at Lady Margaret Hall, University of Oxford, and contributes to the LMH Oxford Summer Programmes. Dr Khan was previously a Research Fellow at the Visual Artificial Intelligence Lab at Oxford Brookes University and a Junior Research Fellow at Lady Margaret Hall, University of Oxford. His research interests include Epistemic Artificial Intelligence, Robust Machine Learning, Continual Learning, Invariant/Covariant Descriptor Design in Machine Learning, and Malicious User Detection in Social Networks. Dr Khan has conceived, designed and delivered several courses on Artificial Intelligence and Machine Learning. He leads on Artificial Intelligence and Machine Learning for the LMH Oxford Summer Programmes.

Available as a Residential or Online course on the following dates:

Session 1: 28th June - 16th July 2027

Session 2: 19th July - 6th August 2027

Session 3: 9th August - 27th August 2027

Click below to find out how to apply.

If you have any questions, or would like to know more, please get in touch via the link below.