Module 1: L6, remarks

Lectures 6 continue learning about CNNs. Specifically, we learn about  

• transfer learning,
• semantic segmentation,
• object detection,
• a few key properties of CNNs (visualisations, adversarial examples, etc). 

Almost all the the videos are from a course at Stanford: http://cs231n.stanford.edu (Länkar till en externa sida.) and the slides from lecture 6 are available here: L6.pdf. See Reading directions and slides from videos for more advices on literature; on that page, we also discuss transformers which has recently (taking off in 2020) become a useful alternative to CNNs for computer vision. 

Finally, a kind advice: pause the videos occasionally to reflect on what you have learned. This will help you understand and remember the material better.