# An unfeasability view of neural network learning

arXiv: https://arxiv.org/abs/2201.00945 · HTML: https://mlsanity.com/paper/2201.00945/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 0 of its 13 references that are in the map.
- First posted on arXiv 4 Jan 2022.

## Abstract (arXiv)

We define the notion of a continuously differentiable perfect learning algorithm for multilayer neural network architectures and show that such algorithms don't exist provided that the length of the data set exceeds the number of involved parameters and the activation functions are logistic, tanh or sin.