Lecture 8 - Multimodal Learning

Teacher: Leopold Maytie (ANITI)

Contents

• Introduction
• Recall
  • MLP
  • CNN
  • RNN
  • Transformers
  • How to train a model
• How to learn from multimodality ?
  • Datasets
  • Methods of fusion, coordination
  • Foundation Models
• Multimodal Tasks
  • Image Captioning
  • Visual Question Answering
  • Multimodal conversational AI system
  • Vision-and-Language Navigation
• Examples of Models
  • CoDi
  • ImageBind
  • BLIP-2
  • CoCa
  • Inner Monologue
  • Palm-E
• Conclusion

Notes

Download the slides here

Tutorial Notebook

Link to Colab Notebook

---

(Back to Main Page)