snntorch
Kilosort
snntorch | Kilosort | |
---|---|---|
2 | 2 | |
1,085 | 402 | |
- | 5.2% | |
9.2 | 9.6 | |
10 days ago | 8 days ago | |
Python | Python | |
MIT License | GNU 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.
snntorch
-
Bio inspired computer vision
Spiking Neural Networks (SNNs): neural networks that use spiking neurons (i.e. neurons that communicate using asynchronous binary spikes similarly to biological neurons) instead of artificial neurons. Apart from this particularity, SNNs can be organized in any kind of topology we all know, like CNNs, ViT, etc. There are tons of approaches to train SNNs, like bio-inspired learning rules (STDP, three factor rules, etc) or adaptations of backprop (which remains the SOTA in a lot of vision tasks). A good resource to begin with backprop-trained SNNs: https://snntorch.readthedocs.io/en/latest/ .
-
How to train brain-inspired spiking neural networks using lessons from deep learning. Interactive Colab notebook links in thread.
Github: https://github.com/jeshraghian/snntorch
Kilosort
-
Is there a whole “layer” of neuroscience that we haven’t uncovered yet?
And yet, we are starting to make sense of it all! The experimental tools are really what makes the difference. Lots of recently developed genetic tools (such as optogenetics ) are now allowing us for the first time to activate/inactivate specific neurons and molecular pathways and observe the causal effects . Other genetic methods (like Crispr) allow us to create mutant animals where a specific gene is mutated, so a lot of work is now in rodents, but I expect it to translate to humans in the next decade or so. Another really crazy one are cerebral organoids, where we grow in vitro a simplified human brain from stem cells to study the details of development and the function of different genetic pathways. When it comes to brain function, the ability to record from tens of thousands of neurons simultaneously using new probes like Neuropixels has been a recent game changer. Also, machine learning approaches are now incredibly useful to analyze data, from detecting the individual "spikes" to developing complex models of the brain dynamics to support computation. To give you a concrete example of progress, we can now read a person's mind so he can write words on a screen, pretty much as quickly as if he was typing them on a keyboard.
-
Clustering Neurons
I'm assuming by clustering neurons, you mean clustering spike data. There are several excellent options that already exist for this purpose, the most notable of which is KiloSort.
What are some alternatives?
spikingjelly - SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
brainflow - BrainFlow is a library intended to obtain, parse and analyze EEG, EMG, ECG and other kinds of data from biosensors
norse - Deep learning with spiking neural networks (SNNs) in PyTorch.
fooof - Parameterizing neural power spectra into periodic & aperiodic components.
bindsnet - Simulation of spiking neural networks (SNNs) using PyTorch.
brainstorm3 - Brainstorm software: MEG, EEG, fNIRS, ECoG, sEEG and electrophysiology
pytorch-forecasting - Time series forecasting with PyTorch
course-content - NMA Computational Neuroscience course
TorchGA - Train PyTorch Models using the Genetic Algorithm with PyGAD
Homer3 - MATLAB application for fNIRS data processing and visualization
pycox - Survival analysis with PyTorch
norse - Deep learning for spiking neural networks