Data

Tools

Indexes

Applications

Experiments

Open Source Science

dendritic_anns

https://github.com/poirazi-lab/dendritic_anns

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.0%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: Poirazi-Lab
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 320 KB
Statistics
  • Stars: 17
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 2
Created over 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

ChavlisPoirazi2024

Dendritic Artificial Neural Networks (dANNs) with Receptive Fields (RFs)

These codes replicate: Chavlis, S., & Poirazi, P (2024). Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning. arXiv:2404.03708v1

To replicate the Figures of the manuscript, you need to install the Anaconda environment (see here)

  1. Download the executable file and install it. Then, create a new environment from a terminal upon activation of anaconda (i.e., conda activate)
  2. conda env create -f environment.yml
  3. conda activate dann

You can run the files .py with python figure_2.py, for example, or train the model using the sh files.

GPU support

You need to install NVIDIA driver, CUDA 12.2 and then install tensorflow, pytorch and jax with cuda compatibility.

You can find your CUDA version with the command: nvcc --version

Tensorflow (https://www.tensorflow.org/install)

python3 -m pip install tensorflow[and-cuda]

and verify the installation: python3 -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"

Pytorch (https://pytorch.org/get-started/locally/)

pip3 install torch torchvision torchaudio

and verify the installation: python3 -c "import torch; print(torch.cuda.is_available())"

Jax (https://jax.readthedocs.io/en/latest/installation.html)

pip install -U "jax[cuda12]"

and verify the installation: python3 -c "from jax.lib import xla_bridge; print(xla_bridge.get_backend().platform)"

CUML installation

pip install --extra-index-url=https://pypi.nvidia.com cuml-cu12

Extract the data

python unzip_data.py

Owner

  • Name: Poirazi Lab
  • Login: Poirazi-Lab
  • Kind: organization
  • Email: software@dendrites.gr
  • Location: Greece

We investigate the role of dendrites in learning and memory processes, using computational models

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Chavlis"
  given-names: "Spyridon"
  orcid: "https://orcid.org/0000-0002-1046-1201"
- family-names: "Poirazi"
  given-names: "Panayiota"
  orcid: "https://orcid.org/0000-0001-6152-595X"
title: "dendritic ANNs for DL architectures"
version: 1.0
doi: 10.5281/zenodo.14360989
date-released: 2024-12-10
url: "https://github.com/Poirazi-Lab/dendritic_anns"

GitHub Events

Total
  • Create event: 1
  • Issues event: 2
  • Release event: 1
  • Watch event: 22
  • Issue comment event: 3
  • Push event: 6
  • Fork event: 2
Last Year
  • Create event: 1
  • Issues event: 2
  • Release event: 1
  • Watch event: 22
  • Issue comment event: 3
  • Push event: 6
  • Fork event: 2

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: about 1 month
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 3.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: about 1 month
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 3.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • rolson24 (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

codes_/requirements.txt pypi
  • keras *
  • matplotlib *
  • numpy *
  • pandas *
  • pingouin *
  • sklearn *
  • tensorflow *
environment.yml pypi
  • absl-py ==2.1.0
  • astunparse ==1.6.3
  • flatbuffers ==24.3.25
  • gast ==0.6.0
  • google-pasta ==0.2.0
  • grpcio ==1.65.5
  • keras ==3.5.0
  • libclang ==18.1.1
  • matplotlib-scalebar ==0.8.1
  • ml-dtypes ==0.4.0
  • namex ==0.0.8
  • opt-einsum ==3.3.0
  • optree ==0.12.1
  • palettable ==3.3.3
  • pooch ==1.8.2
  • seaborn-image ==0.9.0
  • tensorboard ==2.17.1
  • tensorboard-data-server ==0.7.2
  • tensorflow ==2.17.0
  • tensorflow-io-gcs-filesystem ==0.37.1
  • termcolor ==2.4.0