English
Related papers

Related papers: Layer-wise Lipschitz-Product Control for Deep Kolm…

200 papers

Kolmogorov-Arnold Networks (KANs) uniquely combine high accuracy with interpretability, making them valuable for scientific modeling. However, it is unclear a priori how deep a network needs to be for any given task, and deeper KANs can be…

Machine Learning · Computer Science 2025-08-22 James Bagrow , Josh Bongard

Kolmogorov-Arnold networks (KANs) have attracted attention recently as an alternative to multilayer perceptrons (MLPs) for scientific machine learning. However, KANs can be expensive to train, even for relatively small networks. Inspired by…

Machine Learning · Computer Science 2025-11-18 Amanda A. Howard , Bruno Jacob , Sarah Helfert , Alexander Heinlein , Panos Stinis

Kolmogorov-Arnold Networks (KAN) offer universal function approximation using univariate spline compositions without nonlinear activations. In this work, we integrate Error-Correcting Output Codes (ECOC) into the KAN framework to transform…

Machine Learning · Computer Science 2025-09-18 Youngjoon Lee , Jinu Gong , Joonhyuk Kang

Kolmogorov-Arnold Networks (KANs) have garnered attention for replacing fixed activation functions with learnable univariate functions, but they exhibit practical limitations, including high computational costs and performance deficits in…

Machine Learning · Computer Science 2025-07-08 Hanseon Joo , Hayoung Choi , Ook Lee , Minjong Cheon

The Kolmogorov-Arnold representation is a proven adequate replacement of a continuous multivariate function by an hierarchical structure of multiple functions of one variable. The proven existence of such representation inspired many…

Optimization and Control · Mathematics 2020-06-23 Andrew Polar , Michael Poluektov

This paper presents the application of Kolmogorov-Arnold Networks (KAN) in classifying metal surface defects. Specifically, steel surfaces are analyzed to detect defects such as cracks, inclusions, patches, pitted surfaces, and scratches.…

Machine Learning · Computer Science 2025-01-22 Maciej Krzywda , Mariusz Wermiński , Szymon Łukasik , Amir H. Gandomi

Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer…

Machine Learning · Computer Science 2024-09-18 Xingyi Yang , Xinchao Wang

Kolmogorov-Arnold Networks (KANs) have very recently been introduced into the world of machine learning, quickly capturing the attention of the entire community. However, KANs have mostly been tested for approximating complex functions or…

Machine Learning · Computer Science 2025-01-24 Eleonora Poeta , Flavio Giobergia , Eliana Pastor , Tania Cerquitelli , Elena Baralis

Training convolutional neural networks (CNNs) with a strict 1-Lipschitz constraint under the $l_{2}$ norm is useful for adversarial robustness, interpretable gradients and stable training. 1-Lipschitz CNNs are usually designed by enforcing…

Machine Learning · Computer Science 2022-11-17 Sahil Singla , Soheil Feizi

Kolmogorov-Arnold Networks (KANs) introduce a paradigm of neural modeling that implements learnable functions on the edges of the networks, diverging from the traditional node-centric activations in neural networks. This work assesses the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Basim Azam , Naveed Akhtar

We show that any smooth bi-Lipschitz $h$ can be represented exactly as a composition $h_m \circ ... \circ h_1$ of functions $h_1,...,h_m$ that are close to the identity in the sense that each $\left(h_i-\mathrm{Id}\right)$ is Lipschitz, and…

Machine Learning · Computer Science 2018-04-17 Peter L. Bartlett , Steven N. Evans , Philip M. Long

In this article we study high-dimensional approximation capacities of shallow and deep artificial neural networks (ANNs) with the rectified linear unit (ReLU) activation. In particular, it is a key contribution of this work to reveal that…

Numerical Analysis · Mathematics 2023-01-23 Lukas Gonon , Robin Graeber , Arnulf Jentzen

Photonic neural networks promise ultrafast inference, yet most architectures rely on linear optical meshes with electronic nonlinearities, reintroducing optical-electrical-optical bottlenecks. Here we introduce small-scale photonic…

Time series classification is a relevant step supporting decision-making processes in various domains, and deep neural models have shown promising performance in this respect. Despite significant advancements in deep learning, the…

Machine Learning · Computer Science 2025-11-04 Irina Barašin , Blaž Bertalanič , Mihael Mohorčič , Carolina Fortuna

The Kolmogorov-Arnold (KA) representation theorem constructs universal, but highly non-smooth inner functions (the first layer map) in a single (non-linear) hidden layer neural network. Such universal functions have a distinctive local…

Machine Learning · Computer Science 2025-12-03 Michael H. Freedman , Michael Mulligan

A crucial property for achieving secure, trustworthy and interpretable deep learning systems is their robustness: small changes to a system's inputs should not result in large changes to its outputs. Mathematically, this means one strives…

Machine Learning · Computer Science 2024-06-04 Bernd Prach , Christoph H. Lampert

Physics-informed neural networks have proven to be a powerful tool for solving differential equations, leveraging the principles of physics to inform the learning process. However, traditional deep neural networks often face challenges in…

Machine Learning · Computer Science 2024-07-30 Subhajit Patra , Sonali Panda , Bikram Keshari Parida , Mahima Arya , Kurt Jacobs , Denys I. Bondar , Abhijit Sen

Low-latency, resource-efficient neural network inference on FPGAs is essential for applications demanding real-time capability and low power. Lookup table (LUT)-based neural networks are a common solution, combining strong representational…

Hardware Architecture · Computer Science 2026-02-19 Duc Hoang , Aarush Gupta , Philip Harris

Kolmogorov-Arnold Networks (KANs) approximate multivariate functions using learnable univariate edge functions, typically parameterized by B-spline bases. Although effective, spline-based implementations can be computationally expensive. A…

Machine Learning · Statistics 2026-05-22 Roberto Cavoretto , Alessandra De Rossi , Adeeba Haider , Amir Noorizadegan

High-dimensional linear mappings, or linear layers, dominate both the parameter count and the computational cost of most modern deep-learning models. We introduce a general-purpose drop-in replacement, lookup multivariate Kolmogorov-Arnold…

Machine Learning · Computer Science 2025-10-20 Sergey Pozdnyakov , Philippe Schwaller
‹ Prev 1 3 4 5 6 7 10 Next ›