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 hashes)

Uploaded Source

Built Distribution

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

Uploaded Python 3

Supported by

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