|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/deep-learning-with-keras-and-tensorflow-in-r/
课程评论：没有评论
课程名称：《在R中使用Keras和TensorFlow的深度学习》 课程概述：本课程将教您如何从零开始在R中构建强大的卷积神经网络。这种特殊类型的深度网络被广泛应用于学术和实际研究领域，以进行准确预测。如果您希望在图像识别、人脸检测或手写识别等高级任务中使用R语言，那么本课程将是最佳入门选择。我们将以实践为主，逐步详细讲解R中深度学习的卷积神经网络。本课程的精髓在于，您将能够立即应用所学知识，只需简单复制和调整我们在课程中使用的代码。 在构建和训练卷积神经网络的过程中，R语言将利用Python软件的能力。但请放心，您不必学习Python，所有分析都将在R环境中完成。我会告诉您如何从R调用Python函数以创建卷积神经网络。 课程内容包括以下几个部分： 1. 基础知识：开篇介绍卷积神经网络的架构和功能，以通俗易懂的方式，不涉及复杂的数学内容。 2. 技术要求：提供在R中运行Python命令的具体技术要求。 3. 主要内容：专注于构建、训练和评估卷积神经网络。首先，我们将解决两个简单的预测问题，以熟悉卷积神经网络的创建过程。 4. 高级预测：接着进入基于图像的真实高级预测场景，具体学习如何： - 识别人脸（与树木或其他物体的区分） - 识别野生动物图像（如熊、狐狸和老鼠） - 识别特殊字符（如区分星号和井号） - 识别和分类手写数字 课程结束时，您将能在许多实际的图像分类问题中应用所学知识。最后部分的实践练习将帮助您巩固技能。 这是您踏入迷人领域——图像识别与分类的机会。尽管这个领域复杂且要求高，但我们尽力将一切变得简单。立即点击“注册”按钮，获取即时访问权，您一定会获得宝贵的技能。期待在课堂上见到您！
In this course you will learn how to build powerful convolutional neural networks in R, from scratch. This special kind of deep networks is used to make accurate predictions in various fields of research, either academic or practical.If you want to use R for advanced tasks like image recognition, face detection or handwriting recognition, this course is the best place to start. It's a hands-on approach on deep learning in R using convolutional neural networks. All the procedures are explained live, step by step, in every detail.Most important, you will be able to apply immediately what you will learn, by simply replicating and adapting the code we will be using in the course.To build and train convolutional neural networks, the R program uses the capabilities of the Python software. But don't worry if you don't know Python, you won't have to use it! All the analyses will be performed in the R environment. I will tell you exactly what to do so you can call the Python functions from R and create convolutional neural networks.Now let's take a look at what we'll cover in this course.The opening section is meant to provide you with a basic knowledge of convolutional neural networks. We'll talk about the architecture and functioning of these networks in an accessible way, without getting into cumbersome mathematical aspects. Next, I will give you exact instructions concerning the technical requirements for running the Python commands in R.The main sections of the course are dedicated to building, training and evaluating convolutional neural networks.We'll start with two simple prediction problems where the input variable is numeric. These problems will help us get familiar with the process of creating convolutional neural networks.Afterwards we'll go to some real advanced prediction situations, where the input variables are images. Specifically, we will learn to:recognize a human face (distinguish it from a tree - or any other object for that matter)recognize wild animal images (we'll use images with bears, foxes and mice)recognize special characters (distinguish an asterisk from a hashtag)recognize and classify handwritten numbers.At the end of the course you'll be able to apply your knowledge in many image classification problems that you could meet in real life. The practical exercises included in the last section will hopefully help you strengthen you abilities.This course is your opportunity to make the first steps in a fascinating field - image recognition and classification. It is a complex and demanding field, but don't let that scare you. I have tried to make everything as easy as possible.So click the "Enroll" button to get instant access. You will surely acquire some invaluable skills.See you on the other side!
