How AI Learns to See - Convolutional Neural Networks (CNNs)

From David Morgan September 25th, 2023

532 plays 0 comments You unliked the media.

Dive into the mesmerizing world of Convolutional Neural Networks (CNNs) with this comprehensive exploration! Uncover why traditional fully connected networks struggle with large image data, necessitating billions of parameters, especially when adding color channels like RGB. Drawing inspiration from the marvels of the human eye, we introduce the transformative concept of convolution and its profound impact on neural network design. Journey through engaging animations that illuminate how CNNs utilize filters to create diverse feature maps, spotlighting the unique visual patterns each filter captures. Delve into the intricacies of parameter weights and their pivotal role during training. Witness the convergence of AI and parallel computing, culminating in the story of Alex Krizhevsky's revolutionary AlexNet and its innovative use of GPU power. Whether you're an AI enthusiast, student, or just curious, join us in unraveling the fascinating mechanisms that empower AI to 'see' the world around us.

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

Department / Directorate: Mid-Atlantic Region
Media Deployment: Public
iCatalog Course ID: Non Course Related
ICatalog Course ID-2: Non Course Related
ICatalog CourseID-3: Non Course Related
DAU Web Event Series: Not Applicable
Appears In: Artificial Intelligence

Comments
Related Media

Loading…

How AI Learns to See - Convolutional Neural Networks (CNNs)

Related Media