Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/numenta/nupic.torch
Numenta Platform for Intelligent Computing PyTorch libraries
https://github.com/numenta/nupic.torch
htm numenta-platform pytorch
Last synced: 3 days ago
JSON representation
Numenta Platform for Intelligent Computing PyTorch libraries
- Host: GitHub
- URL: https://github.com/numenta/nupic.torch
- Owner: numenta
- License: agpl-3.0
- Created: 2019-03-31T21:25:04.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2024-09-25T15:48:32.000Z (5 months ago)
- Last Synced: 2025-02-10T10:03:40.603Z (10 days ago)
- Topics: htm, numenta-platform, pytorch
- Language: Python
- Homepage: https://nupictorch.readthedocs.io
- Size: 274 KB
- Stars: 283
- Watchers: 48
- Forks: 97
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# Numenta Platform for Intelligent Computing PyTorch libraries
[](https://circleci.com/gh/numenta/nupic.torch)
This library integrates selected neuroscience principles from Hierarchical Temporal Memory (HTM) into the [pytorch](https://pytorch.org/) deep learning platform. The current code aims to replicate how sparsity is enforced via Spatial Pooling, as defined in the paper [*How Could We Be So Dense? The Benefits of Using Highly Sparse Representations*](https://arxiv.org/abs/1903.11257).
For detail on the neuroscience behind these theories, read [Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex](https://numenta.com/neuroscience-research/research-publications/papers/why-neurons-have-thousands-of-synapses-theory-of-sequence-memory-in-neocortex/). For a description of _Spatial Pooling_ in isolation, read [*Spatial Pooling (BAMI)*](https://numenta.com/resources/biological-and-machine-intelligence/spatial-pooling-algorithm/).
`nupic.torch` is named after the original HTM library, the [Numenta Platform for Intelligent Computing (*NuPIC*)](https://github.com/numenta/nupic).
Interested in [contributing](CONTRIBUTING.md)?
## Installation
To install from local source code:
pip install -e .Or using conda:
conda env create
### Test
To run all tests:
pytest
## Examples
We've created a few jupyter notebooks demonstrating how to use **nupic.torch** with standard datasets. You can find these notebooks in the [examples/](https://github.com/numenta/nupic.torch/tree/master/examples/) directory or if you prefer you can open them in [Google Colab](http://colab.research.google.com/github/numenta/nupic.torch/) and start experimenting.
## _Having problems?_
For any installation issues, please [search our forums](https://discourse.numenta.org/search?q=tag%3Ainstallation%20category%3A10) (post questions there). Report bugs [here](https://github.com/numenta/nupic.torch/issues/new/).