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

  1. 【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 ...

  2. 【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 ...

  3. 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 ...

  4. 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 ...

  5. Neural Networks and Deep Learning

    Neural Networks and Deep Learning This is the first course of the deep learning specialization at Co ...

  6. [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 ...

  7. 《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 ...

  8. 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 ...

  9. 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 ...

  10. 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

  1. navicat primium 快捷键与命令

    1.ctrl+q          打开查询窗口 2.ctrl+/           注释sql语句 3.ctrl+shift +/  解除注释 4.ctrl+r          运行查询窗口的s ...

  2. A1129. Recommendation System

    Recommendation system predicts the preference that a user would give to an item. Now you are asked t ...

  3. 利用twilio进行手机短信验证

    首先要注册 twilio 账号但是由于twilio人机验证用的是Goole所有注册需要FQ 完成后去免费获取15元使用 然后 pip install twilio 注册完成后会在个人首页显示你的免费金 ...

  4. JavaScrip相关知识总结

    1.javascript是一种基于对象的语言,其中有四个常用的“全局对象”的成员使用,因为没有“全局对象关键字global”而直接使用,所以感觉像违背了JavaScript基于对象编程的原则,但其实是 ...

  5. vue(基础二)_组件,过滤器,具名插槽

    一.前言 主要包括:  1.组件(全局组件和局部组件)                     2.父组件和子组件之间的通信(单层)                     3.插槽和具名插槽     ...

  6. Go-day04

    今日概要: 1.内置函数.递归函数.闭包 2.数组与切片 3.map数据结构 4.package介绍 5.互斥锁和读写锁 一.内置函数 1.close:主要用来关闭channel 2.len:用来求长 ...

  7. 数据挖掘的标准流程-CRISP-DM

    1.起源 CRISP-DM (cross-industry standard process for data mining), 即为"跨行业数据挖掘过程标准".此KDD(know ...

  8. 二叉树建立及遍历 C++ 源码

    #define _CRT_SECURE_NO_WARNINGS #include<iostream> #include <stdlib.h> using namespace s ...

  9. java io系列21之 InputStreamReader和OutputStreamWriter

    InputStreamReader和OutputStreamWriter 是字节流通向字符流的桥梁:它使用指定的 charset 读写字节并将其解码为字符.InputStreamReader 的作用是 ...

  10. Web API中的返回值类型

    WebApi中的返回值类型大致可分为四种: Void/ IHttpActionResult/ HttpResponseMessage /自定义类型 一.Void void申明方法没有返回值,执行成功后 ...