Coursera, Deep Learning 1, Neural Networks and Deep Learning - week3, Neural Networks Basics
NN representation
这一课主要是讲3层神经网络
下面是常见的 activation 函数.sigmoid, tanh, ReLU, leaky ReLU.
Sigmoid 只用在输出0/1 时候的output layer， 其他情况基本不用，因为tanh 总是比sigmoid 好.
两种 ReLU 使用起来总是要比sigmoid 和 tanh 快。ReLU 是最常用的 activation.
为什么Activation function 要是non-linear的？因为如下图所示如果activation 是linear的，那么最终output 只是 input 的线性函数.
Gradient of activation function
Gredient of 2 layer NN.
Random initialization
Coursera, Deep Learning 1, Neural Networks and Deep Learning - week3, Neural Networks Basics的更多相关文章
- 【DeepLearning学习笔记】Coursera课程《Neural Networks and Deep Learning》——Week2 Neural Networks Basics课堂笔记
Coursera课程<Neural Networks and Deep Learning> deeplearning.ai Week2 Neural Networks Basics 2.1 ...
- 【DeepLearning学习笔记】Coursera课程《Neural Networks and Deep Learning》——Week1 Introduction to deep learning课堂笔记
Coursera课程<Neural Networks and Deep Learning> deeplearning.ai Week1 Introduction to deep learn ...
- 课程一(Neural Networks and Deep Learning)，第四周（Deep Neural Networks） —— 3.Programming Assignments: Deep Neural Network - Application
Deep Neural Network - Application Congratulations! Welcome to the fourth programming exercise of the ...
- 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 ...
- Neural Networks and Deep Learning
Neural Networks and Deep Learning This is the first course of the deep learning specialization at Co ...
- [C3] Andrew Ng - Neural Networks and Deep Learning
About this Course If you want to break into cutting-edge AI, this course will help you do so. Deep l ...
- 《Neural Networks and Deep Learning》课程笔记
Lesson 1 Neural Network and Deep Learning 这篇文章其实是 Coursera 上吴恩达老师的深度学习专业课程的第一门课程的课程笔记. 参考了其他人的笔记继续归纳 ...
- 第四节，Neural Networks and Deep Learning 一书小节(上)
最近花了半个多月把Mchiael Nielsen所写的Neural Networks and Deep Learning这本书看了一遍,受益匪浅. 该书英文原版地址地址:http://neuralne ...
- 课程四(Convolutional Neural Networks)，第二 周（Deep convolutional models: case studies） —— 0.Learning Goals
Learning Goals Understand multiple foundational papers of convolutional neural networks Analyze the ...
- 课程一(Neural Networks and Deep Learning)，第三周（Shallow neural networks）—— 3.Programming Assignment : Planar data classification with a hidden layer
Planar data classification with a hidden layer Welcome to the second programming exercise of the dee ...
随机推荐
- 解题：CF622F The Sum of the k-th Powers
题面 TJOI2018出CF原题弱化版是不是有点太过分了?对,就是 TJOI2018 教科书般的亵渎 然而我这个问题只会那个题的范围的m^3做法 回忆一下1到n求和是二次的,平方求和公式是三次的,立方 ...
- http 请求头和响应头
客户端发送请求过程带着的数据: 1.请求地址 2.请求方式 3.请求头 request headers 4.请求参数 https://www.juhe.cn/ 130.... 1a2b....pei ...
- 点赞功能与redis
转:https://edu.aliyun.com/a/20538 摘要: 前言点赞其实是一个很有意思的功能.基本的设计思路有大致两种, 一种自然是用mysql等数据库直接落地存储, 另外一种就是利用点 ...
- hystrix项目实战
闲话少说: 总共分6步: (1)添加hystrix依赖以及监控的依赖 <dependency> <groupId>org.springframework.cloud</g ...
- scrapy关键字爬取百度图库（一）
刚入门学习python的菜鸟,如有错误,还望指教 爬取百度图库需要知道百度图库的加载方式是通过下拉加载的,所以我们需要分析Ajax请求来爬取每一页的数据信息 表述不清直接上图片 图片一是刷新页面后加载 ...
- (二叉树 BFS DFS) leetcode 104. Maximum Depth of Binary Tree
Given a binary tree, find its maximum depth. The maximum depth is the number of nodes along the long ...
- (string 数组) leetcode 804. Unique Morse Code Words
International Morse Code defines a standard encoding where each letter is mapped to a series of dots ...
- [Luogu 1262] 间谍网络
题目描述 由于外国间谍的大量渗入,国家安全正处于高度的危机之中.如果A间谍手中掌握着关于B间谍的犯罪证据,则称A可以揭发B.有些间谍收受贿赂,只要给他们一定数量的美元,他们就愿意交出手中掌握的全部情报 ...
- IIS 错误：由于扩展配置问题而无法提供您请求的页面。如果该页面是脚本，请添加处理程序。如果应下载文件，请添加 MIME 映射。
HTTP 错误 404.3 - Not Found 由于扩展配置问题而无法提供您请求的页面.如果该页面是脚本,请添加处理程序.如果应下载文件,请添加 MIME 映射. 可能是缺少处理程序映射.默认情况 ...
- CodeForces149D dfs实现区间dp
http://codeforces.com/problemset/problem/149/D 题意 给一个合法的括号串,然后问这串括号有多少种涂色方案,当然啦!涂色是有限制的. 1,每个括号只有三种选 ...