SharpNEAT Publisher's description
from Colin Green
SharpNEAT is an optimised, neuro-evolution framework written in C#.
SharpNEAT is an optimised, neuro-evolution framework written in C#. Included is a front-end GUI, a number of example problem domains and some additional applications for viewing and simulating evolved networks.
What's New in This Release:Major New Features:
В· Support for evolution of acyclic networks.
В· This includes: Development of NeatGenome and associated classes to support efficient evolution of acyclic networks.
В· Development of neural network classes to efficiently execute neural networks.
В· Development of network visualization to layout nodes by layer. This also affects how cylcic networks are laid out because the algorithm that determines which layer a node is in for acylcic nets was extended to also calculate a sensible layer number for cyclic networks, This greatly improves how the networks are laid out with respect to gaining understanding of the network architecture from its visual rendering.
В· Modified all function regression and binary logic themed experiments to use acyclic networks.
В· Added support for Box2D (2D physics engine) based problem domains and visualisation of Box2D worlds with OpenGL.
В· New experiment - Single pole balancing using Box2D, including visualization.
В· New experiment - Inverted double pen...
System Requirements:No special requirements.
Program Release Status: New Release
Program Install Support: Install and Uninstall