<div align="center" style="text-align: center;">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="./docs/source/_static/superneuro-pcg-arrow-dark-tag.svg">
<img alt="SuperNeuroMAT Logo" src="./docs/source/_static/superneuro-pcg-arrow-blue-tag.svg" width='600rem'>
</picture>
</div>
# SuperNeuroMAT
### The Super Speedy Spike Simulator.
SuperNeuroMAT is a Python package for simulating and analyzing spiking neural networks.
[](https://github.com/ORNL/superneuromat/actions/workflows/test.yaml)
[](https://github.com/ORNL/superneuromat/actions/workflows/pages-build.yaml)
[](https://github.com/ORNL/superneuromat/actions/workflows/pypi-release.yml)
Documentation available: https://ORNL.github.io/superneuromat/
[<img src="https://gist.githubusercontent.com/cxmeel/0dbc95191f239b631c3874f4ccf114e2/raw/documentation.svg" alt="Documentation" height="40" />](https://ORNL.github.io/superneuromat/)
Unlike its sister package, [SuperNeuroABM](https://github.com/ORNL/superneuroabm), SuperNeuroMAT uses a matrix-based representation
of the network, which allows for more efficient simulation and GPU acceleration.
SuperNeuroMAT focuses on super-fast computation of Leaky Integrate and Fire **(LIF)** spiking neuron models with STDP.
It provides:
1. Support for leaky integrate and fire neuron model with the following parameters:
* neuron threshold
* neuron leak
* neuron refractory period
2. Support for Spiking-Time-Dependent Plasticity (STDP) on synapses with:
* weight
* delay
* per-synapse disabling of learning
3. Support for all-to-all connections as well as self connections
4. A turing-complete model of neuromorphic computing
5. Optional GPU acceleration or Optional Sparse computation
* Note that long delays may impact performance. Consider using an agent-based simulator
such as [SuperNeuroABM](https://github.com/ORNL/superneuroabm) for longer delays.
## Installation
1. Install using `pip install superneuromat`
2. Update/upgrade using `pip install superneuromat --upgrade`
The [installation guide](https://ORNL.github.io/superneuromat/guide/install.html)
covers virtual environments, faster installation with uv, installing support for CUDA GPU acceleration, and more.
## Usage
Import the spiking neural network class:
```python
from superneuromat import SNN
```
See the [tutorial](https://ORNL.github.io/superneuromat/guide/firstrun.html) for more.
Additionally, the [migration guide](https://ornl.github.io/superneuromat/guide/migration2.html) may be of use to those coming from older versions of SuperNeuroMAT.
## Citation
1. Please cite SuperNeuroMAT using:
```
@inproceedings{date2023superneuro,
title={SuperNeuro: A fast and scalable simulator for neuromorphic computing},
author={Date, Prasanna and Gunaratne, Chathika and R. Kulkarni, Shruti and Patton, Robert and Coletti, Mark and Potok, Thomas},
booktitle={Proceedings of the 2023 International Conference on Neuromorphic Systems},
pages={1--4},
year={2023}
}
```
2. References for SuperNeuroMAT:
- [SuperNeuro: A Fast and Scalable Simulator for Neuromorphic Computing](https://dl.acm.org/doi/abs/10.1145/3589737.3606000)
- [Neuromorphic Computing is Turing-Complete](https://dl.acm.org/doi/abs/10.1145/3546790.3546806)
- [Computational Complexity of Neuromorphic Algorithms](https://dl.acm.org/doi/abs/10.1145/3477145.3477154)
Raw data
{
"_id": null,
"home_page": null,
"name": "superneuromat",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": "Prasanna Date <datepa@ornl.gov>",
"keywords": "Fast Neuromorphic Simulator, Matrix-Based Neuromorphic Simulator, Neuromorphic Algorithms, Neuromorphic Computing, Neuromorphic Simulator, Numpy Neuromorphic Simulator",
"author": "Chathika Gunaratne, Shruti Kulkarni, Robert Patton, Mark Coletti",
"author_email": "Prasanna Date <datepa@ornl.gov>",
"download_url": "https://files.pythonhosted.org/packages/d6/b8/3e969b5c00e5435dd29a5c3c2ad562c33633c694862bf2c96845266a8fea/superneuromat-3.2.1.tar.gz",
"platform": null,
"description": "<div align=\"center\" style=\"text-align: center;\">\n<picture>\n <source media=\"(prefers-color-scheme: dark)\" srcset=\"./docs/source/_static/superneuro-pcg-arrow-dark-tag.svg\">\n <img alt=\"SuperNeuroMAT Logo\" src=\"./docs/source/_static/superneuro-pcg-arrow-blue-tag.svg\" width='600rem'>\n</picture>\n</div>\n\n# SuperNeuroMAT\n\n### The Super Speedy Spike Simulator.\n\nSuperNeuroMAT is a Python package for simulating and analyzing spiking neural networks.\n\n[](https://github.com/ORNL/superneuromat/actions/workflows/test.yaml)\n[](https://github.com/ORNL/superneuromat/actions/workflows/pages-build.yaml)\n[](https://github.com/ORNL/superneuromat/actions/workflows/pypi-release.yml)\n\nDocumentation available: https://ORNL.github.io/superneuromat/\n\n[<img src=\"https://gist.githubusercontent.com/cxmeel/0dbc95191f239b631c3874f4ccf114e2/raw/documentation.svg\" alt=\"Documentation\" height=\"40\" />](https://ORNL.github.io/superneuromat/)\n\nUnlike its sister package, [SuperNeuroABM](https://github.com/ORNL/superneuroabm), SuperNeuroMAT uses a matrix-based representation\nof the network, which allows for more efficient simulation and GPU acceleration.\n\nSuperNeuroMAT focuses on super-fast computation of Leaky Integrate and Fire **(LIF)** spiking neuron models with STDP.\n\nIt provides:\n1. Support for leaky integrate and fire neuron model with the following parameters:\n * neuron threshold\n * neuron leak\n * neuron refractory period\n2. Support for Spiking-Time-Dependent Plasticity (STDP) on synapses with:\n * weight\n * delay\n * per-synapse disabling of learning\n3. Support for all-to-all connections as well as self connections\n4. A turing-complete model of neuromorphic computing\n5. Optional GPU acceleration or Optional Sparse computation\n\n* Note that long delays may impact performance. Consider using an agent-based simulator\nsuch as [SuperNeuroABM](https://github.com/ORNL/superneuroabm) for longer delays.\n\n\n## Installation\n1. Install using `pip install superneuromat`\n2. Update/upgrade using `pip install superneuromat --upgrade`\n\nThe [installation guide](https://ORNL.github.io/superneuromat/guide/install.html)\ncovers virtual environments, faster installation with uv, installing support for CUDA GPU acceleration, and more.\n\n## Usage\nImport the spiking neural network class: \n\n```python\nfrom superneuromat import SNN\n```\n\nSee the [tutorial](https://ORNL.github.io/superneuromat/guide/firstrun.html) for more.\n\nAdditionally, the [migration guide](https://ornl.github.io/superneuromat/guide/migration2.html) may be of use to those coming from older versions of SuperNeuroMAT.\n\n## Citation\n1. Please cite SuperNeuroMAT using:\n\t```\n\t@inproceedings{date2023superneuro,\n\t title={SuperNeuro: A fast and scalable simulator for neuromorphic computing},\n\t author={Date, Prasanna and Gunaratne, Chathika and R. Kulkarni, Shruti and Patton, Robert and Coletti, Mark and Potok, Thomas},\n\t booktitle={Proceedings of the 2023 International Conference on Neuromorphic Systems},\n\t pages={1--4},\n\t year={2023}\n\t}\n\t```\n2. References for SuperNeuroMAT:\n\t- [SuperNeuro: A Fast and Scalable Simulator for Neuromorphic Computing](https://dl.acm.org/doi/abs/10.1145/3589737.3606000)\n\t- [Neuromorphic Computing is Turing-Complete](https://dl.acm.org/doi/abs/10.1145/3546790.3546806)\n\t- [Computational Complexity of Neuromorphic Algorithms](https://dl.acm.org/doi/abs/10.1145/3477145.3477154)\n",
"bugtrack_url": null,
"license": null,
"summary": "A fast and scalable matrix-based simulator for Spiking Neural Networks (SNNs).",
"version": "3.2.1",
"project_urls": {
"Download": "https://pypi.org/project/ini2toml/#files",
"Repository": "https://github.com/ORNL/superneuromat",
"url": "https://github.com/ORNL/superneuromat"
},
"split_keywords": [
"fast neuromorphic simulator",
" matrix-based neuromorphic simulator",
" neuromorphic algorithms",
" neuromorphic computing",
" neuromorphic simulator",
" numpy neuromorphic simulator"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "0f683041fd5f0da334c4de0e00d6ffc0546460bbec75fab4572a0448e58d60b0",
"md5": "ddbec8d368d18715b2cda33f196c772d",
"sha256": "cc61e2a912a0b456899527a50c0aee2b58420b34717b1cb22ddbbd5f2a2ffec7"
},
"downloads": -1,
"filename": "superneuromat-3.2.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ddbec8d368d18715b2cda33f196c772d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 39887,
"upload_time": "2025-07-14T16:48:33",
"upload_time_iso_8601": "2025-07-14T16:48:33.567582Z",
"url": "https://files.pythonhosted.org/packages/0f/68/3041fd5f0da334c4de0e00d6ffc0546460bbec75fab4572a0448e58d60b0/superneuromat-3.2.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d6b83e969b5c00e5435dd29a5c3c2ad562c33633c694862bf2c96845266a8fea",
"md5": "15e5ba2d02ce406d6725cd4e1170f0fb",
"sha256": "8131bcc7c5eab095f696dc3f6dbf4975f33b58b20d9daa642cd46116e2fff2ca"
},
"downloads": -1,
"filename": "superneuromat-3.2.1.tar.gz",
"has_sig": false,
"md5_digest": "15e5ba2d02ce406d6725cd4e1170f0fb",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 173322,
"upload_time": "2025-07-14T16:48:35",
"upload_time_iso_8601": "2025-07-14T16:48:35.280825Z",
"url": "https://files.pythonhosted.org/packages/d6/b8/3e969b5c00e5435dd29a5c3c2ad562c33633c694862bf2c96845266a8fea/superneuromat-3.2.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-14 16:48:35",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ORNL",
"github_project": "superneuromat",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "superneuromat"
}
JSON
