Avoid Overfitting Using Regularization in TensorFlow
Develop an understanding on how to avoid over-fitting with weight regularization and dropout regularization
Be able to apply both weight regularization and dropout regularization in Keras with TensorFlow backend
In this 2-hour long project-based course, you will learn the basics of using weight regularization and dropout regularization to reduce over-fitting in an image classification problem. By the end of this project, you will have created, trained, and evaluated a Neural Network model that, after the training and regularization, will predict image classes of input examples with similar accuracy for both training and validation sets. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.
您要培养的技能
- Data Science
- Deep Learning
- Machine Learning
- Tensorflow
- keras
分步进行学习
在与您的工作区一起在分屏中播放的视频中，您的授课教师将指导您完成每个步骤：
Import the data
Process the data
Regularization and Dropout
Creating the Experiment
Assess the final results
指导项目工作原理
您的工作空间就是浏览器中的云桌面，无需下载
在分屏视频中，您的授课教师会为您提供分步指导
审阅
来自AVOID OVERFITTING USING REGULARIZATION IN TENSORFLOW的热门评论
Good introduction to regularization techniques. It's nice to learn these techniques with a relevant, but simple, example code.
please enable me to reset the deadlines as i was unable to complete..
常见问题
常见问题
如果我购买指导项目，会得到什么？
指导项目可在台式设备和移动设备上学习吗？
指导项目的授课教师是谁？
我能在完成指导项目后从中下载作品吗？
我能够退款吗？退款政策是如何规定的？
有助学金吗？
我能旁听指导项目并免费观看视频部分吗？
我需要具备多少经验才能做这个指导项目？
我能直接通过 Web 浏览器来完成此指导项目，而不必安装特殊软件吗？
指导项目的学习体验如何？
还有其他问题吗？请访问 学生帮助中心。
Coursera Footer
