https://github.com/ajaysub110/mnist-pygenn

Implementation of the paper 'Unsupervised learning of digit recognition using spike-timing-dependent plasticity' by Peter Diehl and Matthew Cook, using the PyGeNN (Python interface of GeNN) SNN framework
https://github.com/ajaysub110/mnist-pygenn

genn machine-learning spiking-neural-networks

Last synced: 3 months ago
JSON representation

Implementation of the paper 'Unsupervised learning of digit recognition using spike-timing-dependent plasticity' by Peter Diehl and Matthew Cook, using the PyGeNN (Python interface of GeNN) SNN framework

• Host: GitHub
• URL: https://github.com/ajaysub110/mnist-pygenn
• Owner: ajaysub110
• Created: 2019-03-21T08:29:34.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2019-10-06T08:50:35.000Z (about 6 years ago)
• Last Synced: 2025-04-07T08:38:02.624Z (6 months ago)
• Topics: genn, machine-learning, spiking-neural-networks
• Language: C++
• Homepage:
• Size: 27.5 MB
• Stars: 12
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          
## MNIST PyGeNN

Implementation of the paper 'Unsupervised learning of digit recognition using spike-timing-dependent plasticity' by Peter Diehl and Matthew Cook, using the PyGeNN (Python interface of GeNN) SNN framework.

### To Do:

- [x] Create LIF neuron, synapse and STDP weight update models

- [x] Create LIF neuron and synapse populations

- [x] Load and prepare MNIST data

- [x] Create Poisson input model and input population with variable frequency

- [x] Write simulation code

- [x] Add training and classification code

- [x] Add lateral inhibition and one vs one connections

- [ ] Obtain results and plot accuracies