Teaching AI on the Edge

Mobile and edge devices are already able to deploy large language models (LLMs) in artificial intelligence (AI) applications that will have a transformational impact on society. How can academia prepare the next generation of engineers to leverage the opportunities and address the challenges presented by AI on the Edge? In this course, Dr. Catherine Breslin, an AI consultant from Cambridge UK and co-founder of Kingfisher Labs, discusses key considerations when teaching AI in higher education. Teaching AI on the Edge is designed to equip educators and learners with the knowledge and skills to successfully implement artificial intelligence in resource-constrained environments. This course blends essential theoretical foundations with practical project-based experiences, preparing you to understand, build, and effectively teach AI systems optimized for edge devices. You'll explore the evolution from specialized task-specific AI models to versatile multimodal foundation models, learning critical techniques such as pruning, quantization, and small-model design that allow advanced AI capabilities to operate efficiently on limited hardware. The course emphasizes iterative development practices, rigorous model evaluation, and responsible AI deployment, highlighting data privacy, model bias, and regulatory considerations. Throughout this course, you'll gain insights into practical teaching strategies that balance theory and hands-on activities, encouraging creative, inclusive, and collaborative approaches to AI education. You'll also discover how to leverage open-source tools and frameworks to accelerate learning and inspire students to tackle real-world problems through innovative edge AI solutions. Join us to deepen your understanding of AI's potential, master effective teaching practices, and inspire the next generation of AI innovators to positively impact society

• Understand foundational AI teaching theories through practical projects
• Effectively teach AI systems optimized for edge devices
• Explore the evolution from specialized to multimodal AI models
• Apply small-model design techniques for efficient AI on limited hardware
• Develop balanced teaching strategies combining theory and practice
• Engage in hands-on activities promoting creativity and inclusivity

• Basic computer and internet skills
• Ability to read course instructions in English and complete short practice activities