Lets build a neural network based scalper together - Page 3
3 页面的第 523 页 FirstFirst 123
Results 21 to 24 of 24

Thread: Lets build a neural network based scalper together

  1. #21
    hi.... i will testing it... i am waiting this one to be develop..

  2. #22
    Thats great.... I can do program little and test a lot..

  3. #23

  4. #24

    Quote Originally Posted by ;
    嗨,神经,我看了看你的源代码,它看起来不像你在规范输入数据。看来您是直接将收盘价输入网络。神经网络数据必须从-1到1或从0到1标准化。
    Agreed. If you are working with data in a range other than [-1;1] or [0;1], then you need to normalize those data. Here is the theory: - You determine the data range. Let say you are working on EURUSD, so your data range will be something like [1.1;1.6] - You convert all data to the range [0;1] (or [-1;1] if needed) - You process the data thru the ANN - You de-scale the resulting outputs using the same original scale. in this case, you convert all data from range [0;1] back to [1.1;1.6]. Here is a function ported in MQL4 from Atmel-C (C-based language used to program Atmel AVR processors) that just do that: Inserted Code double map(double x, double in_min, double in_max, double out_min, double out_max) { return ((x - in_min) * (out_max - out_min)(in_max - in_min) out_min); } Example: To convert x from range [0.5;2.5] to range [0;1]: Inserted Code x2 = map(x,0.5,2.5,0,1);

发布权限

  • 您不可发布新主题
  • 您不可回复
  • 您不可发布附件
  • 您不可编辑您的帖子
  •  
  • BB代码是打开的
  • 表情符号是打开的
  • [IMG]代码是打开的
  • [视频]代码是打开的
  • HTML代码是关闭的
histoforex网站使用cookie 文字跟踪
histoforex网站使用cookie 文字跟踪,某些设定已经固定。您可以点击此处阅读我们的Cookie使用说明。 请点击右键接受我们的cookies。如果您选择继续使用histoforex网站,我们将认为您接受我们的cookies。