Fast Experimentation with Neural Networks
FENNIX is a simulator of artificial neural networks written in Java. It allows you to easily describe a complete simulation by using a simple text script language or by adding nodes to a tree of tasks by using the graphical user interface. You can for instance:
Moreover, FENNIX is composed of pluggable tools that can be easily modified in order to add new functionalities to the simulator.
Last modification 10 April 2012
- Create a dataset by reading a file with observations.
- Create an artificial neural network.
- Find the parameters of the neural network by using different training procedures.
- Test the neural network by applying different measures of performance with different datasets.
- Visualize the results of the training and test phases.
- Export the results and the neural networks.
- Create loops to repeat some parts of the experiment, or use conditionals to control its execution.
by Héctor Satizábal.