executorch
norse
executorch | norse | |
---|---|---|
2 | 6 | |
1,210 | 617 | |
46.4% | 2.6% | |
10.0 | 6.4 | |
2 days ago | 20 days ago | |
C++ | Python | |
GNU General Public License v3.0 or later | GNU Lesser General Public License v3.0 only |
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.
executorch
-
ExecuTorch: Enabling On-Device interference for embedded devices
Yes ExecuTorch is currently targeted at Edge devices. The runtime is written in C++ with 50KB binary size (without kernels) and should run in most of platforms. You are right that we have not integrated to Nvidia backend yet. Have you tried torch.compile() in PyTorch 2.0? It would do the Nvidia optimization for you without Torchscript. If you have specific binary size or edge specific request, feel free to file issues in https://github.com/pytorch/executorch/issues
norse
-
Neuromorphic learning, working memory, and metaplasticity in nanowire networks
This gives you a ludicrous advantage over current neural net accelerators. Specifically 3-5 orders is magnitude in energy and time, as demonstrated in the BranScaleS system https://www.humanbrainproject.eu/en/science-development/focu...
Unfortunately, that doesn't solve the problem of learning. Just because you can build efficient neuromorphic systems doesn't mean that we know how to train them. Briefly put, the problem is that a physical system has physical constraints. You can't just read the global state in NWN and use gradient descent as we would in deep learning. Rather, we have to somehow use local signals to approximate local behaviour that's helpful on a global scale. That's why they use Hebbian learning in the paper (what fires together, wires together), but it's tricky to get right and I haven't personally seen examples that scale to systems/problems of "interesting" sizes. This is basically the frontier of the field: we need local, but generalizable, learning rules that are stable across time and compose freely into higher-order systems.
Regarding educational material, I'm afraid I haven't seen great entries for learning about SNNs in full generality. I co-author a simulator (https://github.com/norse/norse/) based on PyTorch with a few notebook tutorials (https://github.com/norse/notebooks) that may be helpful.
I'm actually working on some open resources/course material for neuromorphic computing. So if you have any wishes/ideas, please do reach out. Like, what would a newcomer be looking for specifically?
-
[D] The Complete Guide to Spiking Neural Networks
Surrogate gradients and BPTT, this is what is implemented in Norse https://github.com/Norse/Norse. It is also possible to compute exact gradients using the Eventprop algorithm.
- [P] Norse - Deep learning with spiking neural networks (SNNs) in PyTorch
- Show HN: Deep learning with spiking neural networks (SNNs) in PyTorch
-
Don't Mess with Backprop: Doubts about Biologically Plausible Deep Learning
That repo is slightly outdated, development now continues at https://github.com/norse/norse.
What are some alternatives?
dfdx - Deep learning in Rust, with shape checked tensors and neural networks
snntorch - Deep and online learning with spiking neural networks in Python
DALI - A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Spiking-Neural-Network - Pure python implementation of SNN
MegEngine - MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架
spikingjelly - SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
candle - Minimalist ML framework for Rust
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
llama - Inference code for Llama models
bindsnet - Simulation of spiking neural networks (SNNs) using PyTorch.
Daisykit - Daisykit is an easy AI toolkit with face mask detection, pose detection, background matting, barcode detection, and more. With Daisykit, you don't need AI knowledge to build AI software.
ocaml-torch - OCaml bindings for PyTorch