Oxford, United Kingdom

Artificial Intelligence and Machine Learning: Advanced Applications of Neural Networks and Deep Learning

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.

In this course students who are already familiar with the key theoretical foundations of Artificial Intelligence and Machine Learning will dive deeper into the exciting capabilities of this area of research and its applications in three streams. First, you will explore Generative Deep Learning and, working with the MNIST and CIFAR-10 datasets, train networks to produce new synthetic samples which appear to belong to the datasets. Secondly, you will learn to design and train Graph Neural Networks, a class of deep learning methods designed to be applied to structured data on irregular grids, such as social network data. Finally, you will look at applications of Reinforcement Learning, a method utilised when you do not have data, but do have access to the data generation process, such as when training a robot to interact with its environment and achieve an objective. This course provides students with an introduction to these advanced topics of Artificial Intelligence and Machine Learning, and provides a solid foundation for future advanced study in the field.

Target group

This course would suit students who are already familiar with the key theoretical foundations of Artificial Intelligence and Machine Learning and wish to expand and further their knowledge and experience. Students must have a good understanding of:
• Neural Networks
• Convolutional Neural Networks
• Deep Learning Libraries
• Optimization
• Numerical Linear Algebra

Course aim

By studying this course you will:
• Be able to assess appropriate Machine Learning techniques and methodologies to be applied to diverse and complex problems.
• Understand how to use Generative Deep Learning tools to train networks to produce synthetic samples of a dataset.
• Learn to design and train Graph Neural Networks.
• Understand varied applications of Reinforcement Learning.

Credits info

7.5 EC
LMH Summer Programmes are designed to be eligible for credit, and we recommend the award of 7.5 ECTS / 4 US / 15 CATS for this course.

Fee info

GBP 1300: This includes:

All tuition, including lectures, seminars, and tutorials.
- Assessment, transcript of academic performance, and certificate.
- Access to the LMH Summer Programmes remote learning platform.
- Support of the dedicated Remote Learning Coordinator.