Skip to main content

A library for deep learning with spiking neural networks

Project description

Myelin

A library to do deep learning with spiking neural networks.

Getting Started

The primary dependencies of this project are torch, tensorflow and OpenAI gym. A more comprehensive list of dependencies can be found in myelin.yml.

Examples

The directory myelin/task contains three example experiments. You can execute them by invoking the run_*.py scripts from this directory.

  • To train a MNIST classification network, invoke
    python run_mnist.py
    
  • To train a CIFAR classification network, invoke
    python run_cifar.py
    
  • To train the cartpole balancing task with Policy gradient, invoke
    python run_gym.py
    

The default choices of hyperparameters are meant as reasonable starting points, they can be improved upon.

License

LGPLv3. See LICENSE for license details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

norse-0.0.0.tar.gz (21.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

norse-0.0.0-py3-none-any.whl (44.9 kB view details)

Uploaded Python 3

File details

Details for the file norse-0.0.0.tar.gz.

File metadata

  • Download URL: norse-0.0.0.tar.gz
  • Upload date:
  • Size: 21.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.3

File hashes

Hashes for norse-0.0.0.tar.gz
Algorithm Hash digest
SHA256 98b17d8a0caad81268c6e3b98f6ec1938f50fd1ce3c52f6d21c5d0d8582cdaaa
MD5 7b1c2d4f66f2f030c5bd02b594093ca4
BLAKE2b-256 09257523711e2318647d0880d41a54a46e81c108090640ba547f29a6df40075a

See more details on using hashes here.

File details

Details for the file norse-0.0.0-py3-none-any.whl.

File metadata

  • Download URL: norse-0.0.0-py3-none-any.whl
  • Upload date:
  • Size: 44.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.3

File hashes

Hashes for norse-0.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a67b0b35d4a188d884b715cefc156192fe0cfcb2ab834761b8dacddf38c2ea06
MD5 fe9bcb8b0d62c92a87039382cb81c1ed
BLAKE2b-256 37dcf03c8e823d93791d1bcae4d82f987d540ec8d8737f351f2ef4999d1ab6d1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page