-
I spoke to @tompollard who is the core maintainer of https://github.com/carpentries-incubator/machine-learning-neural-python.
That lesson takes a different angle to deep learning, focusing on comp…
-
[Adversarial Robustness of Graph Neural Networks](https://mediatum.ub.tum.de/1641938)
```bib
@phdthesis{zugner2022adversarial,
title={Adversarial Robustness of Graph Neural Networks},
author={…
-
[𝑝-Laplacian Based Graph Neural Networks](https://proceedings.mlr.press/v162/fu22e.html)
```bib
@inproceedings{fu2022p,
title={$ p $-Laplacian Based Graph Neural Networks},
author={Fu, Guoji a…
-
Graph neural networks are a popular choice for forecasting hierarchically structured panels, graph structured panels, or structured variable settings, e.g., energy networks with time series observed a…
-
Consideration of the choice between a decision tree and a multilayer neural network. Development of the number of input and output arguments and methods for their parameterization.
-
Neural Networks are powerful but can they count people? Find possible architectures with a few experiments. There are already solutions to count people using object detectors to get bounding boxes and…
-
### Feature description
### Description:
This issue aims to implement an Adaptive Resonance Theory (ART1) algorithm for binary data clustering. ART1 is well-suited for unsupervised learning with bin…
-
+ Read slides [26v4e](https://osf.io/26v4e), [42tq9](https://osf.io/42tq9), [3ksmu](https://osf.io/3ksmu)
+ Obtain access to references given in the slide.
+ Report here with your ID and name.
-
[Towards self-explainable graph neural network](https://dl.acm.org/doi/abs/10.1145/3459637.3482306)
```bib
@inproceedings{dai2021towards,
title={Towards self-explainable graph neural network},
…
-
[Graph neural networks with diverse spectral filtering](https://dl.acm.org/doi/abs/10.1145/3543507.3583324)
```bib
@inproceedings{guo2023graph,
title={Graph neural networks with diverse spectral …