📄 page_92.html

📁 怎样挖掘你的网站的内容。本领域内唯一的书
💻 HTML
字号:
<HTML>  <HEAD>    <!--SCRIPT LANGUAGE="JavaScript" SRC="http://a1835.g.akamai.net/f/1835/276/3h/www.netlibrary.com/include/js/dictionary_library.js"></SCRIPT>    <SCRIPT LANGUAGE="JavaScript">      if (!opener){document.onkeyup=parent.turnBookPage;}    </SCRIPT!-->    <META HTTP-EQUIV="Cache-Control" CONTENT="no-cache">    <META HTTP-EQUIV="Pragma" CONTENT="no-cache">    <META HTTP-EQUIV="Expires" CONTENT="-1"><META http-equiv="Content-Type" content="text/html; charset=windows-1252"><SCRIPT>var PrevPage="Page_91";var NextPage="Page_93";var CurPage="Page_92";var PageOrder="103";</SCRIPT>  <TITLE>Document</TITLE>  </HEAD>  <BODY BGCOLOR="#FFFFFF"><CENTER><TABLE BORDER=0 WIDTH=100% CELLPADDING=0><TR><TD ALIGN=CENTER>  <TABLE BORDER=0 CELLPADDING=2 CELLSPACING=0 WIDTH=100%>  <TR>  <TD ALIGN=LEFT><A HREF='Page_91.html'>Previous</A></TD>  <TD ALIGN=RIGHT><A HREF='Page_93.html'>Next</A></TD>  </TR>  </TABLE></TD></TR><TR><TD ALIGN=LEFT><P><A NAME='JUMPDEST_Page_92'/><A NAME='{326}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0 WIDTH='100%'><TR><TD ALIGN=RIGHT><FONT FACE='Times New Roman, Times, Serif' SIZE=2 COLOR=#FF0000>Page 92</FONT></TD></TR></TABLE><A NAME='{327}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR>  <TD ROWSPAN=5></TD>  <TD COLSPAN=3 HEIGHT=12></TD>  <TD ROWSPAN=5></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR><TD></TD>  <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>The most important factor in the selection of your data is to ensure you include all the ranges of values for all the variables that the network is subject to encounter. In your website, this means including the least and most expensive items and the lowest and highest amounts of sales, session times, units sold, etc. As a rule, you should have several examples in the training set for each value of a categorical attribute and for a range of value for ordered discrete and continuous valued features.</FONT></TD><TD></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR>  <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{328}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR>  <TD ROWSPAN=5></TD>  <TD COLSPAN=3 HEIGHT=12></TD>  <TD ROWSPAN=5></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR><TD></TD>  <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>A trained network has the ability to generalize on unseen data, that is, the ability to correctly assess samples that were not on the training data set. Once you train a network the next step is to test it. Expose the network to samples it has not seen before and observe the network's output. A common methodology is to split your data, training on a portion of your data and testing on the rest. One way to determine the patterns your network is finding difficult to learn is to observe closely the errors it is making. To correct them you can retrain your neural network by giving it more samples of the errors it is having difficulty learning.</FONT></TD><TD></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR>  <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{329}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR>  <TD ROWSPAN=5></TD>  <TD COLSPAN=3 HEIGHT=17></TD>  <TD ROWSPAN=5></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR><TD></TD>  <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3><B>Preparing Your Data</B></FONT></TD><TD></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR>  <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{32A}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR>  <TD ROWSPAN=5></TD>  <TD COLSPAN=3 HEIGHT=12></TD>  <TD ROWSPAN=5></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR><TD></TD>  <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>Real-world data, including that from your website, may be spotty, dirty, or skewed. That is, it may be distributed in an uneven way, making it difficult for a neural network to converge into a good model. A skewed distribution can prevent a network from effectively using an important attribute in your data.</FONT></TD><TD></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR>  <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{32B}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR>  <TD ROWSPAN=5></TD>  <TD COLSPAN=3 HEIGHT=12></TD>  <TD ROWSPAN=5></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR><TD></TD>  <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>A common way to deal with this problem is to &quot;discrete&quot; an attribute. Rather than having a single input for dollar sale amount, you might break it down to several ranges. Here is an example. Let's say your website sells software products that range in price from very low to very high:</FONT></TD><TD></TD></TR><TR>  <TD COLSPAN=3></TD></TR><TR>  <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{32C}'/><TABLE CELLPADDING=0 CELLSPACING=0 BORDER=0 WIDTH='100%'><TR><TD HEIGHT=12></TD></TR><TR><TD><TABLE CELLSPACING=0 WIDTH=583 CELLPADDING=4><TR><TD WIDTH=151 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>$10
⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -