A Java Framework For Complex-Valued Artificial Neural Networks

JACVANN is an open source java framework for complex-valued artificial neural networks. It provides learning algorithms as well as evaluation methods for complex-valued classification problems. Additionally real-valued problems can directly be applied to the complex network using input-encoding-functions and output-functions designed to handle real values.

This website provide an illustrated help for users of the gui-version of JACVANN and JAVCANN.bs, a scripting language to automate processes.

Software and further documentation can be downloaded at the download section.