Using Java Swing to implement backpropagation neural network. Learning algorithm can refer to this Wikipedia page.
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.
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.
git clone https://github.com/Jasonnor/Backpropagation.git cd Backpropagation Backpropagation.jar
- Menu (Files, Skins)
- Background rendering mode & zoom level
- Read the file
- File path
- Adjustable parameters
- Output parameters
- Generate new results
- List of training materials (2/3 of total data)
- List of test data (1/3 of total data)
Be careful to use background rendering mode, and notice that too small drawing size will delay the computer.
Input Data Format
InputA InputB OutputA InputC InputD OutputB ...
You can use these data sets for testing.
Please feel free to use it if you are interested in fixing issues and contributing directly to the code base.
Backpropagation is released under the MIT license. See the LICENSE file for details.