Metadata-Version: 2.4
Name: dendritic_modeling
Version: 0.5.0
Summary: DendriNet: PyTorch library for neural networks of dendritic neurons
Author: Kempner Institute for the Study of Natural and Artificial Intelligence
License-Expression: MIT
Project-URL: Homepage, https://github.com/KempnerInstitute/DendriNet
Project-URL: Documentation, https://kempnerinstitute.github.io/DendriNet/
Project-URL: Source, https://github.com/KempnerInstitute/DendriNet
Project-URL: Issues, https://github.com/KempnerInstitute/DendriNet/issues
Project-URL: Changelog, https://github.com/KempnerInstitute/DendriNet/blob/develop/CHANGELOG.md
Keywords: dendritic,neural-networks,pytorch,machine-learning,neuroscience
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Operating System :: OS Independent
Requires-Python: <4.0,>=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch<3.0.0,>=2.8.0
Requires-Dist: torchvision<1.0.0,>=0.23.0
Requires-Dist: torchinfo>=1.7.0
Requires-Dist: omegaconf<3.0.0,>=2.1.0
Requires-Dist: PyYAML>=6.0
Requires-Dist: numpy<3.0.0,>=1.21.0
Requires-Dist: scipy>=1.7.0
Requires-Dist: scikit-learn>=1.0.0
Requires-Dist: pandas<3.0.0,>=1.3.0
Requires-Dist: matplotlib<4.0.0,>=3.5.0
Requires-Dist: seaborn<1.0.0,>=0.11.0
Requires-Dist: tqdm>=4.60.0
Provides-Extra: test
Requires-Dist: pytest>=7.0.0; extra == "test"
Requires-Dist: pytest-cov>=4.0.0; extra == "test"
Requires-Dist: pytest-timeout>=2.1.0; extra == "test"
Requires-Dist: pytest-xdist>=3.0.0; extra == "test"
Requires-Dist: coverage[toml]>=6.5.0; extra == "test"
Requires-Dist: tomli>=2.0; python_version < "3.11" and extra == "test"
Provides-Extra: lint
Requires-Dist: ruff==0.15.1; extra == "lint"
Requires-Dist: mypy<1.4,>=1.0; extra == "lint"
Requires-Dist: black==24.10.0; extra == "lint"
Requires-Dist: isort==5.13.2; extra == "lint"
Requires-Dist: pre-commit>=3.0.0; extra == "lint"
Provides-Extra: dev
Requires-Dist: dendritic_modeling[lint,test]; extra == "dev"
Requires-Dist: twine>=1.11.0; extra == "dev"
Requires-Dist: setuptools; extra == "dev"
Requires-Dist: wheel; extra == "dev"
Requires-Dist: build; extra == "dev"
Provides-Extra: compression
Requires-Dist: torchao<0.19,>=0.18; extra == "compression"
Provides-Extra: gpu
Requires-Dist: triton>=3.0; extra == "gpu"
Provides-Extra: plotting
Requires-Dist: networkx>=2.6; extra == "plotting"
Provides-Extra: transformers
Requires-Dist: transformers>=4.30; extra == "transformers"
Provides-Extra: train
Requires-Dist: jupyter>=1.0.0; extra == "train"
Requires-Dist: ipykernel; extra == "train"
Requires-Dist: ipython>=8.0.0; extra == "train"
Provides-Extra: docs
Requires-Dist: sphinx>=7; extra == "docs"
Requires-Dist: sphinx-rtd-theme>=2; extra == "docs"
Provides-Extra: all
Requires-Dist: dendritic_modeling[dev,docs,gpu,plotting,train]; extra == "all"
Dynamic: license-file

# DendriNet

DendriNet is a PyTorch library for networks built from dendritic neurons.
It provides branched compartments, sparse excitatory and inhibitory synapses,
shunting and additive integration, population networks, training and analysis.

## Start with an installed example

```bash
dendritic-example synthetic_population --output demo.yaml
dendritic-train demo.yaml --epochs 1
```

This small two-class demonstration generates its data locally. It does not
download a dataset or reproduce a paper result. To start with MNIST instead,
export `mnist_population`; its first run downloads MNIST.

Python 3.10+ and PyTorch 2.8+ are required. The tested CPU environments use
Linux and Python 3.10, 3.11 and 3.12. CUDA is optional. Exact scientific
reproduction requires the study's recorded dependencies, source and settings.

## Graphical model editor

Install the companion distribution `dendrinet-studio` to draw dendritic
populations, trace incoming E and I connections, and compare training runs on
your computer. Launch it with `dendrinet-studio --workspace my-runs`. Designs
export as YAML that the core training command accepts. The
[Studio guide](https://kempnerinstitute.github.io/DendriNet/studio.html)
includes a first run with generated data and a worked synapse-count example.

- [Documentation](https://kempnerinstitute.github.io/DendriNet/)
- [Source and examples](https://github.com/KempnerInstitute/DendriNet)
- [Issues](https://github.com/KempnerInstitute/DendriNet/issues)
- [License: MIT](https://github.com/KempnerInstitute/DendriNet/blob/develop/LICENSE)

The import name is `dendritic_modeling`. Optional extras include `test`, `dev`,
`docs`, `gpu`, `plotting`, `transformers` and `compression`.
