Coursera Machine Learning Week 4 - Neural Networks

最新推荐文章于 2022-02-11 23:07:01 发布

xiewen99

最新推荐文章于 2022-02-11 23:07:01 发布

阅读量1.5w

点赞数

CC 4.0 BY-SA版权

分类专栏：机器学习文章标签：机器学习

本文链接：https://blog.youkuaiyun.com/xiewen99/article/details/52384329

这篇博客探讨了神经网络的表示，包括多层网络的特征计算、过拟合解决方案、逻辑功能的实现、激活函数的计算，以及参数交换对输出的影响。同时提到了在Coursera上的机器学习课程中关于神经网络的编程作业，涉及到多类别分类和神经网络的相关函数实现。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Neural Networks: Representation

(OK) In a neural network with many layers, we think of each successive layer as being able to use the earlier layers as features, so as to be able to compute increasingly complex functions.
(OK) If a neural network is overfitting the data, one solution would be to increase the regularization parameter λ.
If a neural network is overfitting the data, one solution would be to decrease the regularization parameter λ.
Suppose you have a multi-class classification problem with three classes, trained with a 3 layer network. Let a(3)1=(hΘ(x))1 be the activation of the first output unit, and similarly a(3)2=(hΘ(x))2 and a(3)3=(hΘ(x))3. Then for any input x, it must be the case that a(3)1+a(3)2+a(3)3=1.

+1     -20
x1      30     ()     hΘ(x)
x2      30

200万优质内容无限畅学