Author

Á. Hajnal

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

A Geometrical Approach to Constructing Neural Networks for Perfect Training-set Classification

This paper proposes a method for constructing a neural network that achieves perfect classification of all samples in a given training set, without taking regularization into account, and demonstrates that the proposed method achieves perfect training-set classification, and compact models.

Á. Hajnal · 0 citations