MIT Introduction to Deep Learning 6.S191: Lecture 7
New 2020 Edition
Neurosymbolic Hybrid Artificial Intelligence
Lecturer: David Cox
January 2020

Lecture Outline

• 0:00 - Introduction
• 1:25 - Evolution of AI
• 7:32 - MIT-IBM Watson AI Lab
• 10:10 - Why is AI today “narrow”?
• 19:17 - Out-of-distribution performance
• 21:07 - ObjectNet
• 23:04 - Adversarial examples
• 25:24 - When does deep learning struggle?
• 27:00 - Neural networks vs symbolic AI
• 28:38 - Neurosymbolic AI
• 34:20 - Advantages of combining symbolic AI
• 39:01 - CLEVERER and more
• 40:40 - Summary

#ai #artificial-intelligence #machinelearning