⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 index.html

📁 All the tool for build a network able to reconize any shapes. Very complete, a good base for anythi
💻 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>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">
		<table align="center" width="90%" border="0" cellspacing="20" cellpadding="0" height="736">
			<tr>
				<td align="left">
					<b><font size="4">FEED FORWARD NEURAL 
                    NETWORK<span lang="tr">S</span> - A JAVA IMPLEMENTATION v2.0 </font></b>
                    <br>by Aydin Gurel</td>
			</tr>
			<tr>
				<td align="left">
					<u><b>What is this?</b></u><br>
                    This is a java implementation of some types 
                    of feed forward neural networks. You can simulate multilayer 
                    perceptron nets, generalized feed forward nets, modular feed 
                    forward nets using this package. You can use various back 
                    propagation methods. The source code is available and <b>
                    free.</b></td>
			</tr>
			<tr>
				<td align="left">
					<u><b>What can you do with it?</b></u><br>
                    You can:<br>
                    - Build multilayer perceptron, generalized feed forward, 
                    modular feed forward nets;<br>
                    - Train your net using batch, mini batch and incremental 
                    training;<br>
                    - Create pattern sets out of semicolon separated files, 
                    train the net using these patterns,<br>
                    - Spare some of the patterns for cross validation and 
                    testing, calculate error terms out of these patterns;<br>
                    - Load and save network configuration and weights;<br>
                    - Use logistic, tanh and linear activation functions;<br>
                    - Use momentum;<br>
                    - Determine the flatness of the activation functions;<br>
                    - Use different momentum rate, flatness, learning rates for 
                    each neuron.</td>
			</tr>
			<tr>
				<td align="left">
					<u><b>More information</b></u><br>
                    Please see <a href="faq.html">FAQ</a> for more detailed 
                    information.</td>
			</tr>
			<tr>
				<td align="left">
					<u><b>Examples</b></u><br>
                    You can examine three examples, each of which demonstrates 
                    different features of the package.<br>
                    - In <a href="example1.html">example 1</a>; we create a 
                    generalized feed forward net out of a configuration file and 
                    we train it using a set of patterns. We spare some of the 
                    patterns for cross validation and test.<br>
                    - In <a href="example2.html">example 2</a>; we create a 
                    multilayer perceptron and train the net using a set of 
                    patterns.<br>
                    - In <a href="example3.html">example 3</a>; we create a 
                    simple multilayer perceptron and train it incrementally 
                    without using pattern sets.</td>
			</tr>
			<tr>
				<td align="left">
					<u><b>
                    <a href="http://aydingurel.brinkster.net/neural/download.aspx">Download</a></b></u></td>
			</tr>
			<tr>
				<td align="left">
					<u><b>
                    <a href="http://aydingurel.brinkster.net/neural/sendmessage.aspx">Contact</a></b></u><br>
                    The code is free, but please contact me if you wish to use 
                    the code entirely or partially in any kind of project so 
                    that I can reference it and please don't delete the 
                    top lines so that other people can reach this 
                    information. Also, please inform me if you encounter a bug.</td>
			</tr>
			<tr>
				<td align="left">
					<u><b>Previous versions</b></u><br>
                    <a href="http://aydingurel.brinkster.net/neural/1-1/index.html">v1.1</a>&nbsp;&nbsp;
                    <a href="http://aydingurel.brinkster.net/neural/1-0/index.html">v1.0</a></td>
			</tr>
			<tr>
				<td align="center">
					<span lang="tr"><a href="faq.html">FAQ</a> |
                    <a href="example1.html">Example 1</a> |
                    <a href="example2.html">Example 2</a> |
                    <a href="example3.html">Example 3</a> |
                    <a href="http://aydingurel.brinkster.net/neural/download.aspx">
                    Download</a> |
                    <a href="http://aydingurel.brinkster.net/neural/sendmessage.aspx">
                    Contact</a> |
                    <a href="http://aydingurel.brinkster.net/neural/1-1">v1.1</a> 
                    | <a href="http://aydingurel.brinkster.net/neural/1-0">v1.0</a></span></td>
			</tr>
			</table>
	</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 + -