NIR
NIR copied to clipboard
neuromorphs
Neuromorphic Intermediate Representation reference implementation
# Feature: NIR Hub This PR presents a mock example for a new "NIR Hub" feature to the NIR project. The NIR Hub provides a centralized platform where researchers and...
I updated the docs/requirements.txt file, I assume that should help with the dependency issues in the notebooks. Spinnaker2 I couldn't find in pip so that isn't solved here. There seem...
It would be nice to have a list of papers/projects that use NIR on the website, as a central collection of NIR-based projects.
Hey guys, I came across some issues in the documentation of NIR that could use attention: - norse example uses `nir.LI`, which is not implemented in the norse conversion -...
## Summary NIR's type inference system currently requires neuron parameters (tau, v_threshold, etc.) to be arrays with explicit shapes to determine the number of neurons in a layer. This forces...
This initial PR introduces NIRData, an intermediate format for data representations in spiking neural networks. Its purpose is to streamline data exchange across existing simulators and neuromorphic hardware, which currently...
Hello, I'm a student interested in neuromorphic computing. I'm having one problem when I'm converting to NIR using snnTorch, so I'm raising this as an issue. While the instructions are...
In #159 an overview of the supported nodes was initially introduced. This overview is generated by grepping the different NIRNodes in each framework's from_nir or to_nir file. If a NIRNode...
It isn't always clear from the documentation of Primatives what the expected inputs / outputs are. Examples: - Convolutions state the function is f (star) g but then list the...
Right now, we assume (in both type inference and checking) that data/tensors flowing from one node to the next have the exact same shape. PyTorch and other frameworks allow broadcasting,...
Metadata
Owner
Metadata
Neuromorphic Intermediate Representation reference implementation