Machine Learning and Imaging Lecture 10: Ingredients of a Convolutional Neural Network

Описание к видео Machine Learning and Imaging Lecture 10: Ingredients of a Convolutional Neural Network

In this lecture, Dr. Horstmeyer outlines the basic components of a convolutional neural network (CNN). By focusing on the initial task of image classification, Dr. Horstmeyer mathematically defines the input and outputs of a CNN classifier, the operations of the convolutional layers composed of optimized weights, the non-linear and pooling operations that are often used, as well as additional key features that are required for effective operation. After these mathematical introductions, Dr. Horstmeyer then presents and describes a simple CNN within Python and Tensorflow and reviews the key functions and calls used to implement a simple image classification network. Additional resources are available at deepimaging.github.io

Комментарии

Информация по комментариям в разработке

Похожие видео