cifar: fail
gcn on cora: fail
The Expressive Power of Neural Networks: A View from the Width [https://arxiv.org/pdf/1709.02540.pdf]
HOW NEURAL NETWORKS EXTRAPOLATE: FROM FEEDFORWARD TO GRAPH NEURAL NETWORKS [https://arxiv.org/pdf/2009.11848.pdf]
Comparison of non-linear activation functions for deep neural networks on MNIST classification task [https://arxiv.org/pdf/1804.02763.pdf]
Mish: A Self Regularized Non-Monotonic Neural Activation Function [https://arxiv.org/vc/arxiv/papers/1908/1908.08681v2.pdf]