Applied Multi-Modal AI
What this course is
Real work isn’t only text. It’s images, recordings, video, and documents, usually mixed together. This course is about AI systems that work across all of them: describing an image in words, searching a video library by speaking, or building an assistant you can talk to.
You’ll design, test and deploy those prototypes with no-code and low-code tools, and you’ll keep asking who the system is for and what could go wrong. It ends with a portfolio-ready project you built for a real workplace or community need.
Catalog description
Applied systems integrating text, images, audio and video. Using no-code and low-code tools, students design, test and deploy multi-modal prototypes such as image captioning, cross-modal search and voice-enabled assistants. Workforce applications, ethical design, human-centered innovation. Culminates in a portfolio-ready applied project.
- Design applied systems that integrate text, images, audio and video.
- Prototype, test and deploy multi-modal applications such as image captioning, cross-modal search and voice-enabled assistants using no-code and low-code tools.
- Apply ethical design and human-centered innovation to workforce applications of multi-modal AI.
What you'll build
- 1An image captioning or cross-modal search prototypeA working system that connects one kind of media to another, such as describing images in text or finding images from a spoken query.
- 2A voice-enabled assistantAn assistant you can talk to, built with no-code tools and tested for how it handles real speech.
- 3A portfolio-ready applied projectA multi-modal deliverable for a workplace or community need, documented and presentable.
Tools you'll use
No-code and low-code tools. The exact list is set by the instructor each term.