Nandi Schoots — accepted AI-conference papers

2025

Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks

Nandi Schoots, Mattia Jacopo Villani, Niels uit de Bos

AISTATS 2025poster

Kolmogorov-Arnold Networks are a new family of neural network architectures which holds promise for overcoming the curse of dimensionality and has interpretability benefits (Liu et al., 2024). In this paper, we explore the connection between Kolmogorov Arnold Networks (KANs) with piecewise linear (u…

Cited by 0 Source ↗Scholar ↗

2023

A theory of representation learning gives a deep generalisation of kernel methods

Adam X. Yang, Maxime Robeyns, Edward Milsom, Ben Anson, Nandi Schoots, Laurence Aitchison

ICML 2023poster

The successes of modern deep machine learning methods are founded on their ability to transform inputs across multiple layers to build good high-level representations. It is therefore critical to understand this process of representation learning. However, standard theoretical approaches (formally N…

Cited by 22 Source ↗PDF ↗Scholar ↗