rtdl-revisiting-models
lava-dl
rtdl-revisiting-models | lava-dl | |
---|---|---|
1 | 1 | |
156 | 139 | |
4.5% | 4.3% | |
6.6 | 7.8 | |
6 days ago | about 18 hours ago | |
Python | Jupyter Notebook | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" License |
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.
rtdl-revisiting-models
-
[R] New paper on Tabular DL: "On Embeddings for Numerical Features in Tabular Deep Learning"
JFYI: recently, we have split our codebase into separate projects: - https://github.com/Yura52/rtdl - https://github.com/Yura52/tabular-dl-revisiting-models - (the new one) https://github.com/Yura52/tabular-dl-num-embeddings
lava-dl
-
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?
rtdl-num-embeddings - (NeurIPS 2022) On Embeddings for Numerical Features in Tabular Deep Learning
spikingjelly - SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
rtdl - Research on Tabular Deep Learning (Python package & papers) [Moved to: https://github.com/Yura52/rtdl]
learnopencv - Learn OpenCV : C++ and Python Examples
Watermark-Removal-Pytorch - 🔥 CNN for Watermark Removal using Deep Image Prior with Pytorch 🔥.
shap - A game theoretic approach to explain the output of any machine learning model.
conformal_classification - Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).
mnist1d - A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.
threat-research-and-intelligence - BlackBerry Threat Research & Intelligence