ANNarchy (Artificial Neural Networks architect) is a parallel and hybrid simulator for distributed rate-coded or spiking neural networks. The core of the library is written in C++ and distributed using openMP or CUDA. It provides an interface in Python for the definition of the networks. It is released under the GNU GPL v2 or later.
- Source code: github.com/ANNarchy/ANNarchy
- Documentation: annarchy.github.io
- Forum: google forum
- Bug reports and feature requests: Issue Tracker.
Note
ANNarchy 5.0 has been released as pre-release. It is a major update with many new features and improvements. To use the new release, you need to install ANNarchy with pip install ANNarchy==5.0.0rc4. The documentation is available at annarchy.github.io. The documentation for ANNarchy 4.8 is available at annarchy.github.io/ANNarchy4.
If you use ANNarchy for your research, we would appreciate if you cite the following paper:
Vitay J, Dinkelbach HÜ and Hamker FH (2015). ANNarchy: a code generation approach to neural simulations on parallel hardware. Frontiers in Neuroinformatics 9:19. doi:10.3389/fninf.2015.00019
- Julien Vitay (julien.vitay@informatik.tu-chemnitz.de).
- Helge Ülo Dinkelbach (helge-uelo.dinkelbach@informatik.tu-chemnitz.de).
- Fred Hamker (fred.hamker@informatik.tu-chemnitz.de).
Using pip, you can install the latest stable release:
pip install ANNarchySee https://annarchy.github.io/Installation for further instructions.
- GNU/Linux
- MacOS X
- Windows (inside WSL2)
python>= 3.10 (with the development files, e.g.python-devorpython-devel)g++>= 7.4 orclang++>= 3.4cmake>= 3.16setuptools>= 65.0nanobind>= 2.4.0cython>= 3.0numpy>= 1.21sympy>= 1.11scipy>= 1.9matplotlib>= 3.0tqdm>= 4.60
Recommended:
lxml(to save the networks in.xmlformat).h5py(to export data in.h5format).pandoc(forreport()).tensorflow(for theann_to_snn_conversionextension)tensorboardX(for theloggingextension).