zoukankan      html  css  js  c++  java
  • What is neural network?

    It is a powerful learning algoithm inspired by how the brain work.

    Example 1 - single neural network

      Given data ahout the size of houses on the real estate market and you want to fit a function that wil predict their price .It is a linear regression problem beacause the price as function of size continous output.

      We know the prices can never be negative so we are creating a function caled Reactified Linear Unit(ReLU) which starts at zero.

    The input is the size of the house(x)

    The output is the price(y)

    The "neuron" implements the function ReLU (blue line)

    Example 2 - Multiple neural network 

    The price of a house can be affected by other features such as size,number of bedrooms, zip code and wealth .The role of the neural network is to predicted the price and it will automatically generate the hidden units.We only need to give the input x and the output y.

  • 相关阅读:
    nexus
    图片水印
    springmvc+mybatis+spring+redis
    web-fragment模块化使用
    jackson的使用
    httpClient
    ftp上传文件
    windows server 2008 R2中建立ftp站点
    保存网络中的文件
    读取excel文件
  • 原文地址:https://www.cnblogs.com/Davirain/p/8484433.html
Copyright © 2011-2022 走看看