This document provides an overview of Convolutional Neural Networks (CNNs). It defines CNNs as networks that learn multi-level features and perform classification in a joint fashion, performing better than traditional approaches for image and video tasks. The document outlines the typical components of a CNN which are convolution, non-linearity, pooling, and fully connected layers. It also discusses properties of CNNs like sparse interactions and parameter sharing. Applications mentioned include image processing, speech recognition, and natural language processing. In conclusion, CNNs represent a major breakthrough in deep learning with many applications, and ongoing research is important to further develop the technology.