How AI Learns to See Part 2 - A Deeper Dive into CNNs

In this video, we revisit part 1 and the inception of convolutional operations in AI vision. We then dive into the concepts of zero-padding and enhancing our image processing technique. We unpack the mechanism of pooling, with an example illustrating maximum pooling in action. Finally, we explore a detailed example using a multi-layered president-identifying CNN architecture, covering the forward pass, labeled data loss calculations, and backward pass and parameter adjustments. This video is a great introduction to convolutional neural networks (CNNs) and how they can be used for image processing tasks.

CNNs are a type of machine learning model that is particularly well-suited for image recognition and classification tasks. In the video, we explain the basic concepts of CNNs, such as convolutional layers, pooling layers, and fully connected layers. We also show how to use CNNs to build a simple president-identifying system. If you are interested in learning more about CNNs and how to use them for image processing tasks, I encourage you to watch this video.

The link to a course playlist of DAU recommended AI courses is: https://dau.csod.com/ui/lms-learner-playlist/PlaylistDetails?playlistId=00118adb-20e1-4dc5-95a8-9ffd03ab7f70

You will need a DAU account to access these resources. If you are a DoD member and need a DAU account you can request one here: https://www.dau.edu/faq/p/New-DAU-Account