{"id":26187590,"url":"https://github.com/gmum/spatialnetworks","last_synced_at":"2026-03-07T12:35:45.182Z","repository":{"id":75662824,"uuid":"215785953","full_name":"gmum/SpatialNetworks","owner":"gmum","description":"[WIP] Implementation of Biologically-Inspired Spatial Neural Networks (https://arxiv.org/abs/1910.02776)","archived":false,"fork":false,"pushed_at":"2019-11-04T23:12:23.000Z","size":168,"stargazers_count":5,"open_issues_count":0,"forks_count":4,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-04-15T00:48:18.532Z","etag":null,"topics":["biology","brain","deep-learning","dimensions","network","pytorch","spatial"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gmum.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-10-17T12:23:14.000Z","updated_at":"2024-11-14T17:00:41.000Z","dependencies_parsed_at":"2023-04-15T11:54:49.357Z","dependency_job_id":null,"html_url":"https://github.com/gmum/SpatialNetworks","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gmum/SpatialNetworks","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gmum%2FSpatialNetworks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gmum%2FSpatialNetworks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gmum%2FSpatialNetworks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gmum%2FSpatialNetworks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gmum","download_url":"https://codeload.github.com/gmum/SpatialNetworks/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gmum%2FSpatialNetworks/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30213202,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-07T12:15:00.571Z","status":"ssl_error","status_checked_at":"2026-03-07T12:15:00.217Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["biology","brain","deep-learning","dimensions","network","pytorch","spatial"],"created_at":"2025-03-11T23:50:23.848Z","updated_at":"2026-03-07T12:35:45.161Z","avatar_url":"https://github.com/gmum.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [Spatial Neural Networks](https://arxiv.org/abs/1910.02776)\n\n| Version | Docs | Style | Python | PyTorch | Contribute | Roadmap |\n|---------|------|-------|--------|---------|------------|---------|\n| [![Version](https://img.shields.io/static/v1?label=\u0026message=0.0.1\u0026color=377EF0\u0026style=for-the-badge)](https://arxiv.org/abs/1910.02776) | [![Documentation](https://img.shields.io/static/v1?label=\u0026message=docs\u0026color=EE4C2C\u0026style=for-the-badge)](TBD)  | [![style](https://img.shields.io/static/v1?label=\u0026message=CB\u0026color=27A8E0\u0026style=for-the-badge)](TBD) | [![Python](https://img.shields.io/static/v1?label=\u0026message=3.7\u0026color=377EF0\u0026style=for-the-badge\u0026logo=python\u0026logoColor=F8C63D)](https://www.python.org/) | [![PyTorch](https://img.shields.io/static/v1?label=\u0026message=1.2.0\u0026color=EE4C2C\u0026style=for-the-badge)](https://pytorch.org/) | [![Contribute](https://img.shields.io/static/v1?label=\u0026message=guide\u0026color=009688\u0026style=for-the-badge)](https://github.com/szymonmaszke/torchdata/blob/master/CONTRIBUTING.md) | [![Roadmap](https://img.shields.io/static/v1?label=\u0026message=roadmap\u0026color=f50057\u0026style=for-the-badge)](https://github.com/szymonmaszke/torchdata/blob/master/ROADMAP.md)\n\n## 1. Paper abstract ([arxiv](https://arxiv.org/abs/1910.02776))\n\nWe introduce bio-inspired artificial neural networks consisting of neurons that are additionally characterized by spatial positions. \nTo simulate properties of biological systems we add the costs penalizing long connections and the proximity of neurons in a two-dimensional space. \nOur experiments show that in the case where the network performs two different tasks, the neurons naturally split into clusters, \nwhere each cluster is responsible for processing a different task. This behavior \nnot only corresponds to the biological systems, but also allows for further insight into interpretability or continual learning. \n\n## 2. Dependencies\n\nDependencies are gathered inside `requirements.txt`.\nWe advise to use `conda` environment for easier package management.\n\n### 2.1 Setup `conda` [optional]\n\n- Install conda for your specific OS, see instructions [here](https://docs.conda.io/projects/conda/en/latest/user-guide/install/)\n- Create new environment by issuing from shell: `$ conda create --name SpatialNetworks`\n- Activate environment: `$ conda activate SpatialNetworks`\n- Install `pip` within environment: `$ conda install pip`\n\n### 2.2 Install packages\n\nMake sure you have `pip` installed (see [documentation](https://packaging.python.org/tutorials/installing-packages/#ensure-you-can-run-pip-from-the-command-line)) and run:\n\n```\npip install -r requirements.txt\n```\n\nSpecify `--user` flag if needed.\n\n## 3. Performing experiments\n\nExperiments are divided into subsections.\nTo perform specific part use `python main.py \u003csubsection\u003e`.\n\nCurrently following options are available\n\n- `train` - train neural network\n- `record` - record per task activations of neural network for later user\n- `plot` - plot spatial locations of each layer\n- `split` - split networks into task-specific subnetworks via some method\n- `score` - score each network on specific task\n\nIssue `python main.py \u003csubsection\u003e --help` to see available options for each subsection.\n\nTo help with reproducibility later, please wrap your experiments commands with `dvc` (see their [documentation](https://dvc.org/doc)).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgmum%2Fspatialnetworks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgmum%2Fspatialnetworks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgmum%2Fspatialnetworks/lists"}