Скачать с ютуб Lecture 8: CNN Architectures в хорошем качестве

Lecture 8: CNN Architectures

Lecture 8 discusses guidelines for building convolutional neural networks. In the previous lecture we saw that convolutional networks are composed of convolutional layers, pooling layers, nonlinearities, normalization layers, and fully-connected layers; these layers can be combined in a nearly infinite variety of ways. This lecture attempts to bring some order to this multitude of choices by studying design patterns commonly used in historically significant CNN architectures. We also learn how to analyze CNN architectures in terms of their memory usage, parameter counts, and computational complexity. We study common architectures including AlexNet, VGG, GoogLeNet, Residual Networks, DenseNets, and MobileNets. We end with a brief discussion of recent work on neural architecture search. Slides: http://myumi.ch/xmg4d _________________________________________________________________________________________________ Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification and object detection. Recent developments in neural network approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of neural-network based deep learning methods for computer vision. During this course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. We will cover learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks. Course Website: http://myumi.ch/Bo9Ng Instructor: Justin Johnson http://myumi.ch/QA8Pg