norse
Deep learning for spiking neural networks (by electronicvisions)
spikingjelly
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch. (by fangwei123456)
norse | spikingjelly | |
---|---|---|
1 | 1 | |
61 | 1,159 | |
- | - | |
0.0 | 8.7 | |
almost 2 years ago | 7 days ago | |
Python | Python | |
GNU Lesser General Public License v3.0 only | GNU General Public License v3.0 or later |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
norse
Posts with mentions or reviews of norse.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-02-15.
-
Don't Mess with Backprop: Doubts about Biologically Plausible Deep Learning
If you are interested in deep learning with spiking neural networks there is also the norse framework: https://github.com/electronicvisions/norse
spikingjelly
Posts with mentions or reviews of spikingjelly.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-04-04.
-
Has anyone used Spiking Neural Networks (SNNs) for image processing?
Surrogate gradient learning w/ backpropagation: for short, you can use backpropagation with SNNs (by a little trick during the backward pass). Super easy to implement, super efficient. You have a deep SNN trained via backprop with any type of input you want. Personally, that is completely my jam. Maybe you can use such paradigm to easily train an SNN in your biomed image dataset. Good repos: SnnTorch comes with the best tutorials to explain SNNs and surrogate gradient learning. This is the fastest way to understand the field and begin to implement you solution. Nevertheless, spikingjelly remains a better option when it comes to implement your ideas (better memory efficiency, etc). Good mention to lava-dl, with which you can train a neural network and directly transfer it into neuromorphic hardware (Intel Loihi) if you have access to this kind of chip.
What are some alternatives?
When comparing norse and spikingjelly you can also consider the following projects:
bindsnet - Simulation of spiking neural networks (SNNs) using PyTorch.
snntorch - Deep and online learning with spiking neural networks in Python
norse - Deep learning with spiking neural networks (SNNs) in PyTorch.
Spiking-Neural-Network - Pure python implementation of SNN
lava-dl - Deep Learning library for Lava
pytorch-lightning - Build high-performance AI models with PyTorch Lightning (organized PyTorch). Deploy models with Lightning Apps (organized Python to build end-to-end ML systems). [Moved to: https://github.com/Lightning-AI/lightning]
CUDA-Guide - CUDA Guide
tntorch - Tensor Network Learning with PyTorch