Java开源:实现基於反向传播算法的神经网路

xjyh8549 7年前
   <h2>Backpropagation</h2>    <p>Using Java Swing to implement backpropagation neural network. Learning algorithm can refer to this Wikipedia page.</p>    <p>Input consists of several groups of multi-dimensional data set, The data were cut into three parts (each number roughly equal to the same group), 2/3 of the data given to training function, and the remaining 1/3 of the data given to testing function.</p>    <p>The purpose of program is training to cut a number of groups of hyperplanes and synaptic weights, and display the results in the graphical interface.</p>    <h2>Getting Started</h2>    <pre>  git clone https://github.com/Jasonnor/Backpropagation.git  cd Backpropagation  Backpropagation.jar</pre>    <p style="text-align: center;"><img src="https://simg.open-open.com/show/07bca9f09e5cfbd96f9f06107a995894.png"></p>    <ol>     <li>Menu (Files, Skins)</li>     <li>Output</li>     <li>Background rendering mode & zoom level</li>     <li>Read the file</li>     <li>File path</li>     <li>Adjustable parameters</li>     <li>Output parameters</li>     <li>Generate new results</li>     <li>List of training materials (2/3 of total data)</li>     <li>List of test data (1/3 of total data)</li>    </ol>    <p>Be careful to use background rendering mode, and notice that too small drawing size will delay the computer.</p>    <h2>Input Data Format</h2>    <pre>  InputA InputB OutputA  InputC InputD OutputB  ...</pre>    <p>You can use these <a href="/misc/goto?guid=4959742105511309248" rel="nofollow,noindex">data sets</a> for testing.</p>    <h2>Result</h2>    <p style="text-align: center;"><img src="https://simg.open-open.com/show/51800070d14afc42b02de8e7e6e36b83.png"></p>    <p style="text-align: center;"><img src="https://simg.open-open.com/show/dbb2c6eca2bf71443238588ee2a6a208.png"></p>    <p style="text-align: center;"><img src="https://simg.open-open.com/show/0c8f38abea4cf256dc4fc6a613e2dc09.png"></p>    <h2>Contributing</h2>    <p>Please feel free to use it if you are interested in fixing issues and contributing directly to the code base.</p>    <h2>License</h2>    <p>Backpropagation is released under the MIT license. See the <a href="/misc/goto?guid=4959742105612189832" rel="nofollow,noindex">LICENSE</a> file for details.</p>    <p> </p>    <p>来自:https://github.com/Jasonnor/Backpropagation</p>    <p> </p>