Avoid Overfitting Using Regularization in TensorFlow

4.8
64 個評分
提供方
Coursera Project Network
3,038 人已註冊
在此指導項目中,您將:

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

Clock2 hours
Intermediate中級
Cloud無需下載
Video分屏視頻
Comment Dots英語(English)
Laptop僅限桌面

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.

您要培養的技能

Data ScienceDeep LearningMachine LearningTensorflowkeras

分步進行學習

在與您的工作區一起在分屏中播放的視頻中,您的授課教師將指導您完成每個步驟:

  1. Import the data

  2. Process the data

  3. Regularization and Dropout

  4. Creating the Experiment

  5. Assess the final results

指導項目工作原理

您的工作空間就是瀏覽器中的雲桌面,無需下載

在分屏視頻中,您的授課教師會為您提供分步指導

審閱

來自AVOID OVERFITTING USING REGULARIZATION IN TENSORFLOW的熱門評論

查看所有評論

常見問題

常見問題

還有其他問題嗎?請訪問 學生幫助中心