This course has been deprecated and is no longer supported.  For our latest courses on machine learning, consider subscribing to our evergreen curriculums with a subscription package.

Interested in face recognition, fingerprint matching or object recognition? Want to learn tools that can be used to develop the AI of self-driving cars? The key to all of these technologies are Convolutional Neural Networks (CNNs), and this course will teach you how to understand and use them!

Beginning with the solid foundations of exactly what an image is, and how it’s stored in the memory of a computer, you’ll learn:

• The differences between grayscale and color images
• How to address challenges associated with image classification (differences in size or resolution, object position variance, occlusion and more)
• Detecting specific objects in an image using filters (kernels)
• CNN Layers – Convolutions, Pooling, and Fully-Connected Layers

You’ll cement your knowledge by examining case studies on the architectures of various public CNNs, including AlexNet, LeNet5, GoogleNet, and Resnet.