Explicit neural network classifiers for non-separable data

We fully characterize a large class of feedforward neural networks in terms of truncation maps. As an application, we show how a ReLU neural network can implement a feature map which separates concentric data.

@article{ewald2025_2504.18710,
  title={ Explicit neural network classifiers for non-separable data },
  author={ Patrícia Muñoz Ewald },
  journal={arXiv preprint arXiv:2504.18710},
  year={ 2025 }
}