Convolutional Neural Network • CNN

A convolutional neural network (CNN) is a type of neural network that is particularly well suited for image recognition tasks. CNNs work by applying a series of filters to an input image, extracting low-level features, and then combining them to form a higher-level representation. By repeated application of these filters, CNNs are able to learn increasingly complex patterns. For example, a simple filter might detect lines or edges in an image, while a more complex filter might be able to recognize objects such as faces or animals. In recent years, CNNs have achieved remarkable success in a variety of visual tasks, including object classification and detection, scene understanding, and image generation.

MIT Introduction to Deep Learning 6.S191: Lecture 3
Convolutional Neural Networks for Computer Vision
Lecturer: Alexander Amini

A convolutional neural network (CNN) is a type of neural network that is typically used for image classification and recognition tasks. CNNs are similar to traditional neural networks in that they are composed of an input layer, hidden layers, and an output layer. However, CNNs also have an additional component called a convolutional layer. This layer is responsible for extracting features from an input image and then passing them to the next layer. Convolutional layers typically consist of a set of learnable filters, which are used to detect specific patterns in the input data. By repeated application of these filters, CNNs are able to learn increasingly complex representations of the input data. This makes them well-suited for tasks such as image classification, where the goal is to identify objects in an image.