课程一，第四周（Deep Neural Networks） —— 2.Programming Assignments: Deep Neural Network - Application

Posted

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了课程一，第四周（Deep Neural Networks） —— 2.Programming Assignments: Deep Neural Network - Application相关的知识，希望对你有一定的参考价值。

Deep Neural Network - Application

Congratulations! Welcome to the fourth programming exercise of the deep learning specialization. You will now use everything you have learned to build a deep neural network that classifies cat vs. non-cat images.

　　　　　　　　　　　　　　技术分享图片

In the second exercise, you used logistic regression to build cat vs. non-cat images and got a 68% accuracy. Your algorithm will now give you an 80% accuracy! By completing this assignment, you will:

　　- Learn how to use all the helper functions you built in the previous assignment to build a model of any structure you want.

　　- Experiment with different model architectures and see how each one behaves.

　　- Recognize that it is always easier to build your helper functions before attempting to build a neural network from scratch.

This assignment prepares you well for the next course which dives deep into the techniques and strategies for parameters tuning and initializations. Take your time to complete this assignment and make sure you get the expected outputs when working through the different exercises. In some code blocks, you will find a "#GRADED FUNCTION: functionName" comment. Please do not modify it. After you are done, submit your work and check your results. You need to score 70% to pass. Good luck :) !

【中文翻译】

深神经网络-应用
祝贺!欢迎来到深度学习专业第四次编程练习。现在你将使用你所学到的一切建立一个深层的神经网络, 将cat与 non-cat 的图像分类。
在第二个练习中, 您使用逻辑回归来构建 cat 与 non-cat 的图像, 并获得了68% 的准确性。你的算法现在将给你一个80% 的精确度!通过完成此任务, 您将:
　　-了解如何使用在上一个工作分配中生成的所有帮助器函数来构建所需的任何结构的模型。
　　-尝试使用不同的模型体系结构, 并查看每种架构的效果。
　　-认识到, 在尝试从头构建神经网络之前, 构建帮助函数总是比较容易的。
这项任务为您下一课做好了准备。下一课将 深入了解参数调整和初始化的技术和策略。用你的时间完成这个任务, 通过不同的练习，并确保你得到预期的结果 。在某些代码块中, 您将找到一个 "#GRADED FUNCTION: functionName" 的注释。请不要修改它。完成后, 提交您的工作, 并检查您的结果。你需要得分70% 才能过关。祝你好运:)!
-------------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------------
 

以上是关于课程一，第四周（Deep Neural Networks） —— 2.Programming Assignments: Deep Neural Network - Application的主要内容，如果未能解决你的问题，请参考以下文章

课程一(Neural Networks and Deep Learning)总结：Logistic Regression

机器学习001 deeplearning.ai 深度学习课程 Neural Networks and Deep Learning 第一周总结

价值连城 神经网络- 吴恩达Andrew Ng Coursera Neural Networks and Deep Learning

(2012, AlexNet) ImageNet Classification with Deep Convolutional Neural Networks

推荐系统（二十）谷歌YouTubeDNN（Deep Neural Networks for YouTube Recommendations）

Reading Note「7」Deep Forest: Towards an Alternative to Deep Neural Networks