Neural Network

Neural Network



参数 功能
$x_i$ 输入的n维度的向量
$w_i$ 加权的系数
$b$ 偏置
$z$ $\Sigma_{i=1}^{n} w_ix_i+b$ 的值
$h(z)$ 经过激活函数得到的一个范围在0-1之间的数
$a$ 作为输入向量x传给下一个神经元
Read more


— 空 —

​ 这个春节对于每个国人来说,都是一个不一样的春节。各大旅游景点空了,货架上的口罩品类空了,正月的拜年日程空了,城市空了,人心却没有空。全世界都在为武汉加油,为中国加油。

— 数字 —

​ 2月4日0—24时,31个省(自治区、直辖市)和新疆生产建设兵团报告新增确诊病例3887例(湖北省3156例),新增重症病例431例(湖北省377例),新增死亡病例65例(湖北省65例),新增治愈出院病例262例(湖北省125例),新增疑似病例3971例(湖北省1957例)。

​ 24小时实时更新的数字背后,是对患病者的祈祷,是对康复者的祝福,是对离世者的哀悼,更是对无私奉献的医护人员和支援企业及个人的敬礼。

Read more
2019-nCoV Data Prediction

2019-nCoV Data Prediction

2019 Novel Coronavirus (2019-nCoV) is a virus (more specifically, a coronavirus identified as the cause of an outbreak of respiratory illness first detected in Wuhan, China. Early on, many of the patients in the outbreak in Wuhan, China reportedly had some link to a large seafood and animal market, suggesting animal-to-person spread. However, a growing number of patients reportedly have not had exposure to animal markets, indicating person-to-person spread is occurring. At this time, it’s unclear how easily or sustainably this virus is spreading between people. The latest situation summary updates are available on CDC’s web page 2019 Novel Coronavirus, Wuhan, China



As everyone knows, the serious coronavirus is attacking our country especially in Wuhan while most activities are canceled. Staying at home become the daily routine. Besides working on learning stuff, I am trying to learn Python, a popular programming language which I should master long before.

After learning Matrix Linear Regression, an powerful and beginner-friendly algorithm used for predicting, I got an idea: forecasting the future trend by using a series of data including the number of people infected with virus. So I just started to do it and it’s time to share my computing results.

Read more
Intro to Neural Network

Intro to Neural Network


  1. 线性回归可以对样本是非线性的,只要对参数线性


  1. 局部加权回归




  1. 把字用向量表示

  2. 卷积操作

  3. RNN表示

  4. 平均 pool

  5. 全连接

  6. sigmoid