|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/deep-learning-computer-vision
课程评论：没有评论
课程名称：深度学习在计算机视觉中的应用 概述：本课程可作为科罗拉多大学博尔德分校数据科学硕士（MS-DS）学位的一部分，通过Coursera平台进行学习。MS-DS是一个跨学科的学位，结合了应用数学、计算机科学、信息科学等多个部门的教师资源。该项目采取基于表现的招生方式，无需申请流程，适合具备计算机科学、信息科学、数学及统计学等领域多元背景的个人。欲了解更多关于MS-DS课程的信息，请访问 https://www.coursera.org/degrees/master-of-science-data-science-boulder。 课程内容：您将学习计算机视觉作为一个研究领域。我们将探讨多个计算机视觉任务及经典计算机视觉的建议方法，随后引入深度学习方法并应用于相同问题。通过分析结果，我们将讨论两种方法的优势和劣势。此外，我们将使用教程，让学员亲手探索现代机器学习工具和软件库。课程将涵盖深度学习可应用的计算机视觉任务，例如图像分类、带定位的图像分类、目标检测、目标分割、人脸识别以及活动或姿势估计。 大纲： 1. **引言和背景**：学习计算机视觉领域及其目标，即从图像中提取信息，同时了解机器学习和深度学习技术对计算机视觉领域的影响。 2. **经典计算机视觉工具**：探索经典计算机视觉工具和技术，包括卷积操作、线性滤波器及图像特征检测算法。 3. **计算机视觉中的图像分类**：回顾经典计算机视觉中的物体识别挑战，并详细讨论实现物体识别和图像分类的步骤。 4. **神经网络与深度学习**：比较神经网络与经典计算机视觉工具的图像分类流程，复习神经网络的基本组成部分，并通过TensorFlow教程实践构建、训练和使用神经网络进行图像分类预测。 5. **卷积神经网络与深度学习高级工具**：学习卷积神经网络的组成部分，研究描述深度网络的参数与超参数，并探索其在提高深度学习模型准确性中的作用，最后通过TensorFlow教程实践构建、训练和使用深度神经网络进行图像分类。 通过本课程，学员将具备利用深度学习解决计算机视觉问题的能力，掌握相关技术和工具，并在实际应用中提升其技能。
Name:Introduction and Background
Description:In this module, you will learn about the field of Computer Vision. Computer Vision has the goal of extracting information from images. We will go over the major categories of tasks of Computer Vision and we will give examples of applications from each category. With the adoption of Machine Learning and Deep Learning techniques, we will look at how this has impacted the field of Computer Vision.
Name:Classic Computer Vision Tools
Description:In this module, you will learn about classic Computer Vision tools and techniques. We will explore the convolution operation, linear filters, and algorithms for detecting image features.
Name:Image Classification in Computer Vision
Description:In this module we will first review the challenges for object recognition in Classic Computer Vision. Then we will go through the steps of achieving object recognition and image classification in the Classic Computer Vision pipeline.
Name:Neural Networks and Deep Learning
Description:In this module we will compare how the image classification pipeline with neural networks differs than the one with classic computer vision tools. Then we will review the basic components of a neural network. We will conclude with a tutorial in Tensor flow where we will practice how to build, train and use a neural network for image classification predictions.
Name:Convolutional Neural Networks and Deep Learning Advanced Tools
Description:In this module we will learn about the components of Convolutional Neural Networks. We will study the parameters and hyperparameters that describe a deep network and explore their role in improving the accuracy of the deep learning models. We will conclude with a tutorial in Tensor Flow where we will practice building, training and using a deep neural network for image classification.
This course can be taken for academic credit as part of CU Boulder’s Master of Science in Data Science (MS-DS) degree offered on the Coursera platform. The MS-DS is an interdisciplinary degree that brings together faculty from CU Boulder’s departments of Applied Mathematics, Computer Science, Information Science, and others. With performance-based admissions and no application process, the MS-DS is ideal for individuals with a broad range of undergraduate education and/or professional experience in computer science, information science, mathematics, and statistics. Learn more about the MS-DS program at https://www.coursera.org/degrees/master-of-science-data-science-boulder. In this course, you’ll be learning about Computer Vision as a field of study and research. First we’ll be exploring several Computer Vision tasks and suggested approaches, from the classic Computer Vision perspective. Then we’ll introduce Deep Learning methods and apply them to some of the same problems. We will analyze the results and discuss advantages and drawbacks of both types of methods. We'll use tutorials to let you explore hands-on some of the modern machine learning tools and software libraries. Examples of Computer Vision tasks where Deep Learning can be applied include: image classification, image classification with localization, object detection, object segmentation, facial recognition, and activity or pose estimation.
