Demystifying Deep Neural Networks
What are deep neural networks, and how do they work? In this talk, we provide an introduction to deep convolutional neural networks (CNNs), which have recently demonstrated impressive success on a wide range of vision tasks. Without using a lot of complex math, we introduce the basics of CNNs. We explore the differences between shallow and deep networks, and explain why deep learning has only recently become prevalent. We examine the different types of layers used in contemporary CNN designs and illustrate why networks composed of these layers are well suited to vision tasks.