This course serves as an introduction to the practical implementation of deep learning models, focusing on real-world issues. The syllabus includes the exploration of data analysis and visualization, and computer vision, with an emphasis on generative models such as stable diffusion and large language models like ChatGPT.
We encourage students to collaborate in interdisciplinary teams to generate ideas about how, when, and for whom different algorithms can address specific problems in various domains. The course advances through multiple stages of idea presentation and pitching, with the ultimate aim being the development of a preliminary prototype and a compelling pitch by the end of the course.
By the end of this course, students will:
- Gain a better understanding of AI and deep learning models and how they function;
- Develop the ability to build applications using these models;
- Improve critical understanding of data and models, including when to use and when not to use different classes of algorithms.
The course will commence with a presentation of various deep learning and AI models, including a range of example use-cases and critical reflections on their usage. This is designed to inspire students' idea generation on how advanced AI models can be used to solve problems in their specific domains.
Students will then work in groups to develop ideas and build prototypes. Through multiple pitch rounds, these ideas will be refined and discussed collectively. Tutors will provide practical implementation assistance. The final course outcome will be a well-prepared pitch and a minimum viable product (MVP) prototype or mock-up of their project.
This course is open to master students and senior bachelor students. It is recommended that participants possess basic coding knowledge (particularly Python), be comfortable with software usage, be adept at problem-solving, and have a proactive, hands-on approach. |
