https://github.com/thennen/stochasticsynapses.jl
Fast model for large arrays of solid-state stochastic synapses
https://github.com/thennen/stochasticsynapses.jl
emerging-technology gpu julia machine-learning neuromorphic-computing reram stochastic-model synapse
Last synced: 3 months ago
JSON representation
Fast model for large arrays of solid-state stochastic synapses
- Host: GitHub
- URL: https://github.com/thennen/stochasticsynapses.jl
- Owner: thennen
- License: mit
- Created: 2021-12-16T11:33:01.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2024-08-16T08:28:43.000Z (about 1 year ago)
- Last Synced: 2025-07-01T08:07:39.166Z (3 months ago)
- Topics: emerging-technology, gpu, julia, machine-learning, neuromorphic-computing, reram, stochastic-model, synapse
- Language: Julia
- Homepage:
- Size: 9.09 MB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://zenodo.org/badge/latestdoi/438966323)
# StochasticSynapses.jl
This is a Julia implementation of the stochastic synapse model described in [this paper](https://journal.frontiersin.org/article/10.3389/fnins.2022.941753/full).
See a short demo of the switching operation [here](https://www.youtube.com/watch?v=Kk3HzDUP1Vg).
This model has been superseded by [Synaptogen](https://github.com/thennen/Synaptogen).
## Installation
```julia
import Pkg; Pkg.add(url="https://github.com/thennen/StochasticSynapses.jl")
```
## Examples
#### CPU version
```julia
using StochasticSynapses
M = 2^20
# Initialize a million cells
cells = [Cell() for m in 1:M]
# SET all cells to their low resistance state
applyVoltage!.(cells, -2f0)
# Apply random voltages to all cells
voltages = randn(Float32, M)
applyVoltage!.(cells, voltages)
I = Iread.(cells)
```
#### GPU version
```julia
using StochasticSynapses, CUDA
M = 2^20
p = 10
cells = CellArrayGPU(M, p)
voltages = CUDA.randn(M)
applyVoltage!(cells, voltages)
I = Iread(cells)
```