https://github.com/ibm-research-tokyo/diffsnn

An implementation of a differentiable point process and a differentiable spiking neural network.
https://github.com/ibm-research-tokyo/diffsnn

point-processes spiking-neural-networks

Last synced: about 2 months ago
JSON representation

An implementation of a differentiable point process and a differentiable spiking neural network.

• Host: GitHub
• URL: https://github.com/ibm-research-tokyo/diffsnn
• Owner: ibm-research-tokyo
• License: apache-2.0
• Created: 2021-05-25T09:25:58.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2021-06-08T08:58:27.000Z (over 3 years ago)
• Last Synced: 2024-06-17T19:58:53.783Z (3 months ago)
• Topics: point-processes, spiking-neural-networks
• Language: Python
• Homepage:
• Size: 41 KB
• Stars: 20
• Watchers: 4
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
Differentiable Spiking Neural Networks

--------------------------------------

This repository contains Python implementation of a spiking neural network based on point processes.

In particular, a differentiable point process is implemented, which enables us to train a spking neural network with hidden units efficiently.

# How to install

Run

```bash

pip install .

```

# Experiments

See `tasks/synthetic` for experiments using a synthetic data set.

# Reference

Hiroshi Kajino: "A Differentiable Point Process with Its Application to Spiking Neural Networks", ICML-21 [[preprint](https://arxiv.org/abs/2106.00901)].