📄 example1.html
字号:
<html>
<head>
<meta http-equiv="Keywords" content="neural, neural net, neural network, neural programming, mlp, backpropagation, back propagation, multilayer, perceptron, java, java package, example, class, training, train, incremental, batch, mini-batch, mini batch, generalized, modular, feed forward, feed, forward, cross validation, cross, validation, test, free, source, code">
<meta http-equiv="Content-Language" content="en-us">
<meta http-equiv="Description" content="This work is a java implementation of feed forward neural nets. Using this package, you can easily build and train multilayer, generalized feed forward, modular feed forward nets with any number of layers and any number of units.">
<title>Example 1 - FEED FORWARD NEURAL NETWORKS - A JAVA IMPLEMENTATION
v2.0</title>
<META HTTP-EQUIV="pragma" CONTENT="no-cache">
<META HTTP-EQUIV="Expires" CONTENT="Fri, 30 May 1980 01:00:00 GMT">
</head>
<body bgcolor="#e2e0e0" style="font-family: Verdana">
<div align="center">
<center>
<table width="90%" border="0" cellspacing="20" cellpadding="0" style="border-collapse: collapse" bordercolor="#111111">
<tr>
<td align="left">
<a href="index.html">Home</a></td>
</tr>
<tr>
<td align="left">
<b><font size="4"><a name="top"></a>FEED FORWARD NEURAL
NETWORK<span lang="tr">S</span> - A JAVA IMPLEMENTATION v2.0 </font></b>
<br><font size="5"><b>Example 1</b></font></td>
</tr>
<tr>
<td align="left">
In this example, we:<br>
<br>
- Create a generalized feed forward net using a previously
saved configuration.<br>
- Create a pattern set with 2 input and 1 output values;
randomly choose 80% of data for training, 10% for cross
validation, 10% for testing. The function to be learned is:
y = x1 + x2.<br>
- Display the error rate (crossvalerror) before training.<br>
- Train it using batch training until crossvalerror < 0.02
so that it learns how to compute a simple function such as y
= x1 + x2. Note that this is one of the easiest function to
learn. If we had chosen another function instead of y = x1 +
x2, we would need much more training.<br>
- Check the error using test data (testerror).<br>
- Save its weights.<br>
- Clean up the objects which are used in the example.<br>
- Recreate the net using previously saved configuration and
weigts and use the trained net to calculate some numbers
(you could use this part in a separate java class).<br>
<br>
<img border="0" src="example1.gif" width="250" height="260"></td>
</tr>
<tr>
<td align="left">
<a href="index.html">Home</a></td>
</tr>
</table>
</center>
</div>
</body>
</html>⌨️ 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 + -