?? page_93.html
字號:
<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_92";var NextPage="Page_94";var CurPage="Page_93";var PageOrder="104";</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_92.html'>Previous</A></TD> <TD ALIGN=RIGHT><A HREF='Page_94.html'>Next</A></TD> </TR> </TABLE></TD></TR><TR><TD ALIGN=LEFT><P><A NAME='JUMPDEST_Page_93'/><A NAME='{32F}'/><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 93</FONT></TD></TR></TABLE><A NAME='{330}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0 WIDTH='100%'><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 ALIGN=CENTER><FONT FACE='Times New Roman, Times, Serif' SIZE=3><IMG SRC='0093-01.JPG' BORDER=0 ALT='0093-01.jpg' WIDTH=440 HEIGHT=140></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{331}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0 WIDTH='100%'><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 ALIGN=CENTER><FONT FACE='Times New Roman, Times, Serif' SIZE=2>Figure 3-7 <BR>Common features captured and transformed during a web session. </FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{332}'/><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>functionality. Another technique for dealing with skewed and categorical data is to use their logarithmic or square root value, as well as doing "1-of-N" conversions, as the above sample demonstrates.</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{333}'/><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>During the initial phase of using a neural network tool, you will need to train it using examples of website sessions in which actual sales took place. The samples need to reflect as many features as you can possibly capture, such as when the sale was made and who made it (Figure 3-7). However, since a neural network works best when all inputs and outputs are between 0 and 1, certain conversions need to be made from the web-generated data. Both continuous and categorical values need to be converted—a process which good data mining tools are able to do relatively easy.</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{334}'/><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>Webbing Your Features</B></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{335}'/><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>Date and time fields can be inputted into your website's neural network in one of two ways. Any date can be represented as is and left as a single number for a specific day in a month. A variable such as a length of connection in seconds or minutes can also be represented as a fixed point in time. Because you are looking at patterns of transactions in your website, you may want to do some conversions of dates, in order to detect trends in ads, marketing campaigns, seasonal or network cycles, etc. For example, you may want to extract a date and deal with it as an additional input into your network:</FONT><FONT FACE='Times New Roman, Times, Serif' SIZE=3 COLOR=#FFFF00><!-- break --></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{336}'/><TABLE CELLPADDING=0 CELLSPACING=0 BORDER=0 WIDTH='100%'><TR><TD HEIGHT=12></TD></TR><TR><TD><TABLE CELLSPACING=0 WIDTH=583 CELLPADDING=5><TR><TD WIDTH=199 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2><B>Access Date</B></FONT></TD><TD WIDTH=144 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2><B>Day of the Week</B></FONT></TD><TD WIDTH=240 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2><B>Additional Input</B></FONT></TD></TR><TR><TD WIDTH=199 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>030299</FONT></TD><TD WIDTH=144 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>Monday</FONT></TD><TD WIDTH=240 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>00001</FONT></TD></TR><TR><TD WIDTH=199 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>030399</FONT></TD><TD WIDTH=144 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>Tuesday</FONT></TD><TD WIDTH=240 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>00010</FONT></TD></TR><TR><TD WIDTH=199 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>030499</FONT></TD><TD WIDTH=144 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>Wednesday</FONT></TD><TD WIDTH=240 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>00100</FONT></TD></TR><TR><TD WIDTH=199 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>030599</FONT></TD><TD WIDTH=144 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>Thursday</FONT></TD><TD WIDTH=240 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>01000</FONT></TD></TR><TR><TD WIDTH=199 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>030699</FONT></TD><TD WIDTH=144 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>Friday</FONT></TD><TD WIDTH=240 VALIGN=TOP><FONT FACE='Times New Roman, Times, Serif' SIZE=2>10000</FONT></TD></TR></TABLE></TD></TR></TABLE><BR><A NAME='{337}'/></FORM></P></TD></TR></TABLE><P><FONT SIZE=0 COLOR=WHITE></CENTER><A NAME="bottom"> </A><!-- netLibrary.com Copyright Notice --> </BODY></HTML>?? 快捷鍵說明
復制代碼
Ctrl + C
搜索代碼
Ctrl + F
全屏模式
F11
切換主題
Ctrl + Shift + D
顯示快捷鍵
?
增大字號
Ctrl + =
減小字號
Ctrl + -