📄 page_89.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_88";var NextPage="Page_90";var CurPage="Page_89";var PageOrder="100";</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_88.html'>Previous</A></TD> <TD ALIGN=RIGHT><A HREF='Page_90.html'>Next</A></TD> </TR> </TABLE></TD></TR><TR><TD ALIGN=LEFT><P><A NAME='JUMPDEST_Page_89'/><A NAME='{30C}'/><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 89</FONT></TD></TR></TABLE><A NAME='{30D}'/><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='0089-01.GIF' BORDER=0 ALT='0089-01.gif' WIDTH=346 HEIGHT=91></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{30E}'/><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 3-3 <BR>This network with a hidden layer allows it to recognize patterns.</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{30F}'/><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='0089-02.GIF' BORDER=0 ALT='0089-02.gif' WIDTH=137 HEIGHT=86></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{310}'/><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 3-4<BR>The Simple XOR Function.</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{311}'/><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='0089-03.GIF' BORDER=0 ALT='0089-03.gif' WIDTH=335 HEIGHT=262></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{312}'/><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 3-5<BR> XOR function using linear threshold<BR> units in a backpropagation network.</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{313}'/><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 neuron will output a 0, and if the sum of the inputs is less than .01, then the output will be 1. After applying a training pattern of 1 on each of the two inputs, the neurons' outputs are computed and adjusted, as Figure 3-6 shows.</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{314}'/><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>Each of the neuron's output is noted for each node along with the sum of the neuron's internal signals. Neurons <I>a</I> and <I>b</I> are both sending 1's to the next layer. Neuron <I>x</I> gets two signals, one from neuron <I>a</I> and one from neuron <I>b.</I> The weight from neurons <I>a</I> to neuron<I> x</I> is W<I>xa,</I> and its value is ⌨️ 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 + -