arXiv Open Access 2025

Computing Linear Regions in Neural Networks with Skip Connections

Johnny Joyce Jan Verschelde

Lihat Sumber

Abstrak

Neural networks are important tools in machine learning. Representing piecewise linear activation functions with tropical arithmetic enables the application of tropical geometry. Algorithms are presented to compute regions where the neural networks are linear maps. Through computational experiments, we provide insights on the difficulty to train neural networks, in particular on the problems of overfitting and on the benefits of skip connections.

Topik & Kata Kunci

cs.LG cs.SC

Penulis (2)

Johnny Joyce

Jan Verschelde

Format Sitasi

APA MLA BibTeX

Joyce, J., Verschelde, J. (2025). Computing Linear Regions in Neural Networks with Skip Connections. https://arxiv.org/abs/2509.15441

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓