The NEAT package contains source code implementing the NeuroEvolution of Augmenting Topologies method. The source code is written in C++. NEAT is a method for evolving speciated neural networks of arbitrary structures and sizes. NEAT leverages the evolution of structure to make neuroevolution more efficient. For more information on NEAT, see the
original publication or our
Neuroevolution page.
The package includes implementations of experiments for XOR, single pole balancing, and both Markovian and non-Markovian double pole balancing.
For answers to common questions, refer to our FAQ .
Please contact kstanley@cs.utexas.edu for comments, including ideas or plans for expanding the open source software.
Versions:
- v1.0 8/16/01 kstanley
- v1.1 7/14/02 kstanley
- removed extraneous files from package
- fixed array bound error
- made text output default on instead of off
- v1.2 7/19/10 kstanley & ikarpov
- Re-release package under Apache 2.0 license per authors' request
- Fix compilation errors with GCC 4.x.x and above
- Make sure neat requires the paramfile command line argument.
- Update README file
- v1.2.1 8/20/11 erkin
- Fix typo in NNode::depth() causing max_depth to be calculated incorrectly.
- Fix Makefile optimization flag and a few minor memory issues.
- Fix a performance regression with the Markovian double pole balancing experiment, mainly by increasing weight caps.
- Consider failed runs when printing the average number of evaluations.