100 Days of Deep Learning - CNN Backpropagation Part 2 | How Backpropagation works on Convolution, Maxpooling and Flatten Layers

This video explains in great detail how the backpropagation algorithm works in the case of CNN. We will learn how to apply backprop on flatten, maxpooling and convolution layers. I recommend you watch the 1st part before watching this one. Here is the link: https://www.youtube.com/watch?v=RvCCFttGFMY&ab_channel=CampusX Notes: https://learnwith.campusx.in/s/store/courses/YouTube%20Notes ============================ Do you want to learn from me? Check my affordable mentorship program at : https://learnwith.campusx.in ============================ 📱 Grow with us: CampusX' LinkedIn: https://www.linkedin.com/company/campusx-official CampusX on Instagram for daily tips: https://www.instagram.com/campusx.official My LinkedIn: https://www.linkedin.com/in/nitish-singh-03412789 Discord: https://discord.gg/PsWu8R87Z8 👍If you find this video helpful, consider giving it a thumbs up and subscribing for more educational videos on data science! 💭Share your thoughts, experiences, or questions in the comments below. I love hearing from you! ⌚Time Stamps⌚ 00:00 - intro 00:05 - Backpropagation in CNN explained for convolution, max pooling, and flatten layers 01:23 - Recap/Back Propogation in CNN 02:46 - Backpropagation involves applying gradients to update weights and calculate loss 07:46 - Changing w1 affects Z1. 11:53 - Backpropagation in Maxpooling Layers 17:31 - Backpropagation on max pooling works by selecting the maximum item in each window 21:23 - The Backpropagation process involves minimizing the inverse of max pooling and calculating the derivative of Z1. 25:07 - Backpropagation process for Convolution, Maxpooling, and Flatten layers 30:48 - Backpropagation involves expanding and differentiating expressions to calculate derivatives. 36:35 - Backpropagation involves multiplication and deconvolution operations.