1. Abrahamsen, M., Kleist, L., Miltzow, T.: Training neural networks is $$\exists {\mathbb{R} }$$-complete. Adv. Neural. Inf. Process. Syst. 34, 18293–18306 (2021)
2. Anthony, M., Bartlett, P.L.: Neural network learning: Theoretical foundations. cambridge university press (1999)
3. Arora, R., Basu, A., Mianjy, P., Mukherjee, A.: Understanding deep neural networks with rectified linear units. In: International Conference on Learning Representations (2018)
4. Bartlett, P.L., Harvey, N., Liaw, C., Mehrabian, A.: Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks (2017)
5. Bertschinger, D., Hertrich, C., Jungeblut, P., Miltzow, T., Weber, S.: Training fully connected neural networks is $$\exists {\mathbb{R}}$$-complete. arXiv preprint arXiv:2204.01368 (2022)