DeepLearning.AI recently introduced a new course, ‘Multimodal RAG: Chat with Videos’ offered by Andrew Ng, founder and CEO in collaboration with Intel Corporation, and taught by Vasudev Lal, Principal AI Research Scientist at Intel Labs.
Focusing on building a system that answers grounded responses from video content. In this course, participants will create an interactive chat system using the BridgeTower model, a multimodal transformer developed by Intel and Microsoft Research.
Click here to check out the course.
This course aims at helping participants generate joint embeddings from video content and store them in a vector database building a Retrieval-Augmented Generation (RAG) pipeline to fetch relevant video data using Large Vision-Language Models (LVLMs) to answer questions using both text and image inputs.
By the end of the course, participants will be able to build systems that can intelligently interact with video content. Participants will also make API calls to access multimodal models hosted by Prediction Guard on Intel’s cloud.
Andrew Ng, has recently joined the Korea’s National AI Committee as advisors. His recent appointment to the National AI Committee comes on the heels of a series of educational initiatives launched through DeepLearning.AI.
Last month, DeepLearning unveiled a course on federated learning, allowing secure training on private data, alongside a partnership with Flower Labs.
DeepLearning.AI have also expanded their generative AI course offerings to cater to learners at various skill levels. Courses range from foundational topics like LLMs and diffusion models to practical applications such as building chatbots and automating workflows with ChatGPT.
The post DeepLearning.AI Launches ‘Multimodal RAG: Chat with Videos’ Course with Intel appeared first on AIM.
