Overview
This course on Neurosymbolic AI aims to introduce learners to the concept of combining neural networks with symbolic AI to create more advanced artificial intelligence systems. By the end of the course, students will understand the evolution of AI, the limitations of current AI systems, and the advantages of integrating symbolic reasoning with deep learning. The course covers topics such as out-of-distribution performance, adversarial examples, and the challenges faced by deep learning. The teaching method includes lectures with slides and real-world examples. This course is intended for individuals interested in deep learning, artificial intelligence, and the future of AI technologies.
Syllabus
- Introduction
- Evolution of AI
- MIT-IBM Watson AI Lab
- Why is AI today "narrow"?
- Out-of-distribution performance
- ObjectNet
- Adversarial examples
- When does deep learning struggle?
- Neural networks vs symbolic AI
- Neurosymbolic AI
- Advantages of combining symbolic AI
- CLEVERER and more
- Summary
Taught by
https://www.youtube.com/@AAmini/videos