What is TIKAPP?
Tool collection
TIKAPP is becoming a collection of tools for simulation of neural networks. The first available part is an ANSI-C++ library with support for multi-layer perceptron networks. Backpropagation and Quickprop are available as training algorithms. There is also an example implementation of a graphical NN-simulator.
Open Source and Cross Plattform
All parts of TIKAPP are developed in ANSI C++ and are published under GNU Public License (GPL).
Features
- Multi-layer feedforward neural networks
- Backpropagation training with momentum, weight decay and flat-spot elimination support
- Quickprop training
- XML based network saving and loading
Download
Source and binary packages of the current release are available from here. Previous releases can be downloaded from the project home at SourceForge.net.
