2 August 2024
on course website
Advanced Artificial Intelligence and Machine Learning: Computer Vision
From self-driving cars and augmented reality to intelligent medical imaging helping doctors identify diseases more quickly, computer vision is a rapidly-growing field within artificial intelligence and machine learning. 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.
You will begin with computer vision algorithms for classification, recognition, detection, and their implementation in deep learning libraries, before exploring autoencoders and variational autoencoders, and gaining insights into the training and application of generative adversarial networks. You will proceed to an in-depth examination of diffusion models, including score-based diffusion models, latent diffusion models, and Stable Diffusion. The final part of the course explores even more advanced topics, including the representation of 3D objects, vision transformers, video classification, and text to image generation.
This intensive course offers students theoretical understanding and practical experience in a range of advanced computer vision concepts and techniques, offering career skills as well as excellent foundations for future research.
This course would suit STEM students with intermediate level experience in artificial intelligence, machine learning, and computer vision concepts and techniques, including those undertaking, or looking ahead to, graduate level study or research.
Specifically, students on this course must have experience of the following topics:
- Knowledge of the deep learning libraries.
- Understanding of deep learning and convolutional neural networks.
- Strong background in optimization and probability.
- Familiarity with the Python programming language.
By the end of this course, you will:
- Understand computer vision algorithms for classification, recognition, and detection, and their implementation in deep learning libraries.
- Know the different types of generative adversarial network and their distinct contributions to controlled data synthesis and image generation.
- Be able to identify different diffusion models and assess their advantages in generative modeling.
- Be able to demonstrate awareness and understanding of the latest key research areas in computer vision.
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.
GBP 3980: This includes:
- All tuition, including lectures, seminars, and tutorials.
- Assessment, transcript of academic performance, and certificate.
- A co-curricular programme of skills workshops and guest speakers.
- Access to the Lady Margaret Hall College Library.
- Bed & Breakfast accommodation throughout your programme.
- Lunch and dinner in the College Dining Hall Monday to Friday.
- A full Social & Cultural Programme, including two excursions to other English cities per three-week programme session.
- A high-quality printed class photograph.
- Formal Graduation banquet.
on course website