[ML of Andrew Ng]Week 4 Neural Networks: Representation
2016-03-16 11:05
513 查看
Week 4 Neural Networks: Representation
Week 4 Neural Networks RepresentationNon-linear hypotheses
Neurons and the brain
Neural Networks
The brain
Model representation
Neurons in the brain
Neural Network
Examples
Multi-class classification
Non-linear hypotheses
So, simple logistic regression together with adding in maybe the quadratic or the cubic features that’s just not a good way to learn complex nonlinear hypotheses when n is large because you just end up with too many features.Neural Networks turns out to be a much better way to learn complex hypotheses, complex nonlinear hypotheses even when your input feature space, even when n is large.
Neurons and the brain
Neural Networks
Origins: Algorithms that try to mimic the brain.Was very widely used in 80s and early 90s; popularity diminished in late 90s.
Recent resurgence: State-of-the-art technique for many applications
The brain
This is fascinating hypothesis that the way the brain does all of these different things is not worth like a thousand different programs, but instead, the way the brain does it is worth just a single learning algorithm.Model representation
Neurons in the brain
Neural Network
Attention:x0=+1,call bias.
Examples
We put it together to make a three-layer neural network to get x1 XNOR x2
Multi-class classification
We use the index of max as predict.In matlab:
[~,p] = max(all_p,[],2);
相关文章推荐
- 深入 String 类
- 创建表
- 深入解析C++设计模式编程中解释器模式的运用
- MyEclipse 2015 运行tomcat 内存溢出的解决方法
- javaScript事件
- 三维激光扫描技术入门
- MyBatis HelloWorld
- Linux内核的整体架构
- maven中dependencies与dependencyManagement的区别
- request和response中文乱码
- 获取当前的日期时间 格式“yyyy-MM-dd HH:MM:SS"
- 如何在maven项目的pom.xml文件中添加jar包
- 3月3号周练——2015 Multi-University Training Contest 7
- 《Linux内核设计与实现》第一二章读书笔记
- axis2 以 RPC的方式访问webservice
- Selenium - How does the Selenium WebDriver work?
- Android界面设计适配不同屏幕的尺寸和密度解读
- python abc
- 二叉树的存储和构造例子
- iOS沙盒机制