havFmNet:J Released!! The JAVA version of our popular havFmNet++ Feature Mapping Neural Net class library - Buy it now!.

JavaTM classes for implementing 1D to nD Self-Organizing Feature Maps Questions? Feel free to drop by and chat if you have any questions - one of us is usually around during normal CST/CDT business hours. havFmNet:J is focused on implementation of the underlying NN functions/activities rather than the higher-level simulator/UI. It is designed to be fully embedable; however, it can, as easily, be used to implement stand-alone training or consultation applications. The typical application can take advantage of the layer oriented API to define either simple nets or very complicated and large nets consisting of one or more sub-nets. Features 1D to nD maps with fully "hyper" neighborhood function and parameters. Notice: The JavaScript Neural Nets web-demo contains a conultation application using a 3-D Map trained using havFmNet:J. Neighborhood controlable by function width, coefficient cutoff and block size (i.e. hypercube size). Nodes addressable by 1D or nD index values. Error query per map or per node Selectable conscience, learning rate, batch size, noise, etc. On-Center-Off-Surround training with a sombrero form of Kohonen's neighborhood function. Click for larger view We would be glad to send you any further information that you might need. Do you by any chance have access to FrameMaker or can you read postscript or .pdf files? If so, we can send some manual excerpts. Alternatively, you might give us a call at (281) 341-5035 in order to discuss you application and how the hav.Software NN libraries can help.