课程一(Neural Networks and Deep Learning),第三周(Shallow neural networks)—— 1、两层神经网络的单样本向量化表示与多样本向量化表示
如上图所示的两层神经网络,
单样本向量化: 多样本向量化:
for i=1 to 4:
z[1](i) = W[1](i) x(i) + b[1](i) Z[1] = W[1] X+ b[1]
(4,1) (4,3) (3,1) (4,1) (4,4) (4,3) (3,4) (4,4)
a[1](i) =sigmoid( z[1](i) ) A[1] = sigmoid( Z[1] )
(4,1) (4,1) (4,4) (4,4)
z[2](i) = W[2](i) a[1](i) + b[2](i) Z[2] = W[2] A[1] + b[2]
(1,1) (1,4) (4,1) (1,1) (1,4) (1,4) (4,4) [1,4]
a[2](i) =sigmoid( z[2](i) ) A[2] = sigmoid( Z[2] )
(1,1) (1,1) (1,4) (1,4)
课程一(Neural Networks and Deep Learning),第三周(Shallow neural networks)—— 1、两层神经网络的单样本向量化表示与多样本向量化表示的更多相关文章
- Deep Learning入门视频(上)_一层/两层神经网络code
关于在51CTO上的深度学习入门课程视频(9)中的code进行解释与总结: (1)单层神经网络: #coding:cp936 #建立单层神经网络,训练四个样本, import numpy as np ...
- 吴恩达《深度学习》-第一门课 (Neural Networks and Deep Learning)-第三周:浅层神经网络(Shallow neural networks) -课程笔记
第三周:浅层神经网络(Shallow neural networks) 3.1 神经网络概述(Neural Network Overview) 使用符号$ ^{[
- 【面向代码】学习 Deep Learning(三)Convolution Neural Network(CNN)
========================================================================================== 最近一直在看Dee ...
- 课程一(Neural Networks and Deep Learning),第二周(Basics of Neural Network programming)—— 4、Logistic Regression with a Neural Network mindset
Logistic Regression with a Neural Network mindset Welcome to the first (required) programming exerci ...
- 课程一(Neural Networks and Deep Learning),第一周(Introduction to Deep Learning)—— 2、10个测验题
1.What does the analogy “AI is the new electricity” refer to? (B) A. Through the “smart grid”, AI i ...
- 课程一(Neural Networks and Deep Learning),第一周(Introduction to Deep Learning)—— 1、经常提及的问题
Frequently Asked Questions Congratulations to be part of the first class of the Deep Learning Specia ...
- 课程一(Neural Networks and Deep Learning),第二周(Basics of Neural Network programming)—— 3、Python Basics with numpy (optional)
Python Basics with numpy (optional)Welcome to your first (Optional) programming exercise of the deep ...
- 课程一(Neural Networks and Deep Learning),第一周(Introduction to Deep Learning)—— 0、学习目标
1. Understand the major trends driving the rise of deep learning.2. Be able to explain how deep lear ...
- 课程一(Neural Networks and Deep Learning),第二周(Basics of Neural Network programming)—— 0、学习目标
1. Build a logistic regression model, structured as a shallow neural network2. Implement the main st ...
- 课程一(Neural Networks and Deep Learning),第二周(Basics of Neural Network programming)—— 2、编程作业常见问题与答案(Programming Assignment FAQ)
Please note that when you are working on the programming exercise you will find comments that say &q ...
随机推荐
- FontAwesome 4.7.0 中完整的675个图标样式CSS参考
FontAwesome 4.7.0 中完整的675个图标样式CSS参考 用法:首先引入CSS文件:<link href="https://maxcdn.bootstrapcdn.com ...
- openstack的Host Aggregates和Availability Zones
1.关系 Availability Zones 通常是对 computes 节点上的资源在小的区域内进行逻辑上的分组和隔离.例如在同一个数据中心,我们可以将 Availability Zones 规划 ...
- 第32章:MongoDB-索引--Capped固定集合
①Capped集合(固定集合) Capped集合的大小固定,性能好,如果空间用完了,新的对象会覆盖旧的对象. find时默认就是插入的顺序,Capped集合会自动维护. ②语法 db.createCo ...
- UVaLive 4628 Jack's socks (贪心)
题意:给定一个无向图,让你把所有点的和它的任意一个相邻点匹配起来,问你是方案是不是唯一,如果是,则输出方案. 析:贪心,很容易知道,如果一个点的度数是 1,那么它只有一个相邻点,这样的话,我们就可以把 ...
- WordPaster-KesionCMS V9整合教程
注意:KesionCMS V9使用的是JQuery 1.10.3版本.需要到JQuery UI官网下载JQuery 1.10.3的UI库. JQueryUI官网:http://jqueryui.com ...
- 2.1.6synchronized锁重入
关键字在使用synchronized时,当线程得到一个对象锁时,这时这个线程再次请求此对象锁是可以拿到的,也就说明同步方法之间是可以进行互相调用的, package com.cky.bean; /** ...
- (动态规划)Max Sum Plus Plus--hdu--1024
http://acm.hdu.edu.cn/showproblem.php?pid=1024 Max Sum Plus Plus Time Limit: 2000/1000 MS (Java/Othe ...
- POJ3104--Drying(Binary Search)
It is very hard to wash and especially to dry clothes in winter. But Jane is a very smart girl. She ...
- Java的String类
String类 String是引用数据类型:字符串是String类的对象 String类的构造方法 共有13种重载方式,这里只示例常用的几个 String():创建一个空字符串 String(Stri ...
- POJ3020 Antenna Placement
Antenna Placement Time Limit: 1000MS Memory Limit: 65536K Total Submissions: 9586 Accepted: 4736 ...