English
Related papers

Related papers: Polynomial, trigonometric, and tropical activation…

200 papers

Different activation functions work best for different deep learning models. To exploit this, we leverage recent advancements in gradient-based search techniques for neural architectures to efficiently identify high-performing activation…

Machine Learning · Computer Science 2024-08-14 Lukas Strack , Mahmoud Safari , Frank Hutter

In this paper a new class of radial basis functions based on hyperbolic trigonometric functions will be introduced and studied. We focus on the properties of their generalised Fourier transforms with asymptotics. Therefore we will compute…

Numerical Analysis · Mathematics 2025-05-21 Martin Buhmann , Joaquín Jódar , Miguel L. Rodríguez

The asymptotic mean squared test error and sensitivity of the Random Features Regression model (RFR) have been recently studied. We build on this work and identify in closed-form the family of Activation Functions (AFs) that minimize a…

Machine Learning · Statistics 2023-03-28 Jianxin Wang , José Bento

This paper presents a comprehensive survey of 18 distinct polynomials and their potential applications in Kolmogorov-Arnold Network (KAN) models as an alternative to traditional spline-based methods. The polynomials are classified into…

Machine Learning · Computer Science 2024-10-15 Seyd Teymoor Seydi

The operational calculus associated with Hermite numbers has been shown to be an effective tool for simplifying the study of special functions. Within this context, Hermite polynomials have been viewed as Newton binomials, with the…

Number Theory · Mathematics 2026-04-23 Giuseppe Dattoli , Subuhi Khan , Ujair Ahmad

The operational calculus associated with special polynomials has proven to be a powerful tool for analyzing and simplifying their properties. This article examines the bivariate degenerate Hermite polynomials with a focus on their…

Classical Analysis and ODEs · Mathematics 2025-09-01 Nusrat Raza , Ujair Ahmad , Subuhi Khan

Activation functions play a key role in neural networks so it becomes fundamental to understand their advantages and disadvantages in order to achieve better performances. This paper will first introduce common types of non linear…

Machine Learning · Computer Science 2018-04-10 Dabal Pedamonti

We make the case for neural network objects and extend an already existing neural network calculus explained in detail in Chapter 2 on \cite{bigbook}. Our aim will be to show that, yes, indeed, it makes sense to talk about neural network…

Machine Learning · Computer Science 2024-02-05 Shakil Rafi , Joshua Lee Padgett , Ukash Nakarmi

Double descent presents a counter-intuitive aspect within the machine learning domain, and researchers have observed its manifestation in various models and tasks. While some theoretical explanations have been proposed for this phenomenon…

Machine Learning · Computer Science 2024-05-14 Yufei Gu

This paper analyses both nonlinear activation functions and spatial max-pooling for Deep Convolutional Neural Networks (DCNNs) by means of the algebraic basis of mathematical morphology. Additionally, a general family of activation…

Machine Learning · Computer Science 2022-07-15 Santiago Velasco-Forero , Jesús Angulo

In this paper, we investigate the geometric structure of activation spaces of fully connected layers in neural networks and then show applications of this study. We propose an efficient approximation algorithm to characterize the convex…

Machine Learning · Computer Science 2019-04-03 Yuting Jia , Haiwen Wang , Shuo Shao , Huan Long , Yunsong Zhou , Xinbing Wang

We discuss a novel analysis method for reaction network systems with polynomial or rational rate functions. This method is based on computing tropical equilibrations defined by the equality of at least two dominant monomials of opposite…

Molecular Networks · Quantitative Biology 2015-08-25 Satya Swarup Samal , Dima Grigoriev , Holger Fröhlich , Ovidiu Radulescu

Spectral methods are an important part of scientific computing's arsenal for solving partial differential equations (PDEs). However, their applicability and effectiveness depend crucially on the choice of basis functions used to expand the…

Numerical Analysis · Mathematics 2021-11-10 Brek Meuris , Saad Qadeer , Panos Stinis

Success of deep neural networks in diverse tasks across domains of computer vision, speech recognition and natural language processing, has necessitated understanding the dynamics of training process and also working of trained models. Two…

Computer Vision and Pattern Recognition · Computer Science 2021-09-06 Yogesh Kochar , Sunil Kumar Vengalil , Neelam Sinha

Quantum signal processing is a powerful framework in quantum algorithms, playing a central role in Hamiltonian simulation and related applications. The sequence of polynomials implemented at each step of this protocol provides a polynomial…

Quantum Physics · Physics 2026-05-08 Pierre-Antoine Bernard , Nathan Wiebe

The use of operational methods of different nature is shown to be a fairly powerful tool to study different problems regarding the theory of Legendre and Legendre-like polynomials. We show how the use of the well known integral…

Classical Analysis and ODEs · Mathematics 2020-02-17 S. Licciardi , G. Dattoli , R. M. Pidatell

In this paper, we introduce a novel non-linear activation function that spontaneously induces class-compactness and regularization in the embedding space of neural networks. The function is dubbed DOME for Difference Of Mirrored Exponential…

Machine Learning · Computer Science 2021-12-08 Mohamed E. Hussein , Wael AbdAlmageed

In this article we present a method to implement orthogonal polynomials and many other special functions in Computer Algebra systems enabling the user to work with those functions appropriately, and in particular to verify different types…

Classical Analysis and ODEs · Mathematics 2016-09-06 Wolfram Koepf

Threshold activation functions are highly preferable in neural networks due to their efficiency in hardware implementations. Moreover, their mode of operation is more interpretable and resembles that of biological neurons. However,…

Machine Learning · Computer Science 2023-03-07 Tolga Ergen , Halil Ibrahim Gulluk , Jonathan Lacotte , Mert Pilanci

Deep neural networks work well at approximating complicated functions when provided with data and trained by gradient descent methods. At the same time, there is a vast amount of existing functions that programmatically solve different…

Machine Learning · Computer Science 2019-01-15 Alon Jacovi , Guy Hadash , Einat Kermany , Boaz Carmeli , Ofer Lavi , George Kour , Jonathan Berant