Research

Publications

Software

Coneural's scientists have developed several software packages that can be used as research tools:

Thyrix

Thyrix (developed by Razvan Florian) is a fast agent/environment simulator designed for artificial intelligence or artificial life research. It is optimized for speed, and thus it is very appropriate for evolutionary experiments. Thyrix allows the simulation of agents with articulated arms or bodies that interact with objects within a 2D environment with Aristotelian physics. The simulator includes a stable collision resolution system and a fast algorithm for solving the constraints generated by the articulations.

Thyrix Lite contains the core of the simulator and can be downloaded as free, open-source software. Thyrix Pro allows fast simulation of articulated agents.

Thyrix home page

SpikeNNS

SpikeNNS (developed by Ioana Goga) represents an extension of SNNS - Stuttgart Neural Network Simulator for the simulation of spiking neural networks. The neural model implemented is based on a simplified version of the Spike Response Model. Neurons are simulated with a limited number of parameters that include: postsynaptic potential, threshold, noise, delays, refractoriness. The SpikeNNS was designed to produce biologically inspired models of cognitive phenomena based on a spike-coding neural model. SpikeNNS is free, open-source software.

SpikeNNS home page

Neocortex, RetinotopicNet

Neocortex and RetinotopicNet are two efficient simulators for large scale spiking neural networks, developed by Raul Muresan. For more information, see the following papers:

R.C. Muresan, I. Ignat (2004), The "Neocortex" Neural Simulator: A Modern Design. International Conference on Intelligent Engineering Systems, September 19-21, 2004, Cluj-Napoca, Romania.

R.C. Muresan, I. Ignat (2004). Principles of Design for Large Scale Neural Simulators. International Conference on Automation, Quality and Testing, Robotics, May 13-15, 2004, Cluj-Napoca, Romania.

R. C. Muresan (2003), RetinotopicNET: An efficient simulator for retinotopic visual architectures, Proceedings of the European Symposium on Artificial Neural Networks, Bruges, Belgium, pp. 247-254.