English
Related papers

Related papers: Approximating Activation Functions

200 papers

This paper develops simple feed-forward neural networks that achieve the universal approximation property for all continuous functions with a fixed finite number of neurons. These neural networks are simple because they are designed with a…

Machine Learning · Computer Science 2022-10-10 Zuowei Shen , Haizhao Yang , Shijun Zhang

Artificial neural networks usually consist of successive linear multiply-accumulate operations and nonlinear activation functions. However, most optical neural networks only achieve the linear operation in the optical domain, while the…

Optics · Physics 2023-11-03 Guanting Liu , Yiwei Shen , Ruiqian Li , Jingyi Yu , Xuming He , Cheng Wang

The widespread application of artificial neural networks has prompted researchers to experiment with FPGA and customized ASIC designs to speed up their computation. These implementation efforts have generally focused on weight…

Neural and Evolutionary Computing · Computer Science 2018-10-23 Tao Yang , Yadong Wei , Zhijun Tu , Haolun Zeng , Michel A. Kinsy , Nanning Zheng , Pengju Ren

In this article we present new results on neural networks with linear threshold activation functions. We precisely characterize the class of functions that are representable by such neural networks and show that 2 hidden layers are…

Machine Learning · Computer Science 2023-10-20 Sammy Khalife , Hongyu Cheng , Amitabh Basu

This paper studies the approximation capacity of ReLU neural networks with norm constraint on the weights. We prove upper and lower bounds on the approximation error of these networks for smooth function classes. The lower bound is derived…

Machine Learning · Computer Science 2023-03-31 Yuling Jiao , Yang Wang , Yunfei Yang

Smooth activation functions are ubiquitous in modern deep learning, yet their theoretical advantages over non-smooth counterparts remain poorly understood. In this work, we study both approximation and statistical properties of neural…

Machine Learning · Statistics 2026-03-03 Yuhao Liu , Zilin Wang , Lei Wu , Shaobo Zhang

This paper studies the approximation capacity of neural networks with an arbitrary activation function and with norm constraint on the weights. Upper and lower bounds on the approximation error of these networks are computed for smooth…

Numerical Analysis · Mathematics 2025-12-24 Francesco Paolo Maiale , Anastasiia Trofimova , Arturo De Marinis

Understanding the computational complexity of training simple neural networks with rectified linear units (ReLUs) has recently been a subject of intensive research. Closing gaps and complementing results from the literature, we present…

Machine Learning · Computer Science 2022-08-24 Vincent Froese , Christoph Hertrich , Rolf Niedermeier

In this paper we present a modified version of the Hyperbolic Tangent Activation Function as a learning unit generator for neural networks. The function uses an integer calibration constant as an approximation to the Euler number, e, based…

Neural and Evolutionary Computing · Computer Science 2017-07-06 Vincent Ike Anireh , Emmanuel Ndidi Osegi

Effective activation functions introduce non-linear transformations, providing neural networks with stronger fitting capa-bilities, which help them better adapt to real data distributions. Huawei Noah's Lab believes that dynamic activation…

Computer Vision and Pattern Recognition · Computer Science 2024-09-16 Chuan Feng , Xi Lin , Shiping Zhu , Hongkang Shi , Maojie Tang , Hua Huang

Dynamic adaptation in single-neuron response plays a fundamental role in neural coding in biological neural networks. Yet, most neural activation functions used in artificial networks are fixed and mostly considered as an inconsequential…

Machine Learning · Computer Science 2020-06-23 Victor Geadah , Giancarlo Kerg , Stefan Horoi , Guy Wolf , Guillaume Lajoie

Transformers have revolutionized natural language processing, but their use for numerical computation has received less attention. We study the approximation of matrix functions, which map scalar functions to matrices, using neural networks…

Machine Learning · Computer Science 2026-02-10 Rahul Padmanabhan , Simone Brugiapaglia

In this paper, we construct neural networks with ReLU, sine and $2^x$ as activation functions. For general continuous $f$ defined on $[0,1]^d$ with continuity modulus $\omega_f(\cdot)$, we construct ReLU-sine-$2^x$ networks that enjoy an…

Machine Learning · Computer Science 2022-08-16 Yuling Jiao , Yanming Lai , Xiliang Lu , Fengru Wang , Jerry Zhijian Yang , Yuanyuan Yang

We consider neural network approximation spaces that classify functions according to the rate at which they can be approximated (with error measured in $L^p$) by ReLU neural networks with an increasing number of coefficients, subject to…

Functional Analysis · Mathematics 2021-10-29 Philipp Grohs , Felix Voigtlaender

Researchers have proposed various activation functions. These activation functions help the deep network to learn non-linear behavior with a significant effect on training dynamics and task performance. The performance of these activations…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Pravendra Singh , Munender Varshney , Vinay P. Namboodiri

This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Archisman Chakraborti , Bidyut B Chaudhuri

Recently there has been much interest in understanding why deep neural networks are preferred to shallow networks. We show that, for a large class of piecewise smooth functions, the number of neurons needed by a shallow network to…

Machine Learning · Computer Science 2017-03-07 Shiyu Liang , R. Srikant

In this paper, we prove that a shallow neural network with a monotone sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function can arbitrarily well approximate any L^p(p>=2) integrable functions defined on R*[0,1]^n. We also prove…

Machine Learning · Computer Science 2021-10-12 Ming-Xi Wang , Yang Qu

ReLU, a commonly used activation function in deep neural networks, is prone to the issue of "Dying ReLU". Several enhanced versions, such as ELU, SeLU, and Swish, have been introduced and are considered to be less commonly utilized.…

Machine Learning · Computer Science 2024-07-12 Jamshaid Ul Rahman , Rubiqa Zulfiqar , Asad Khan , Nimra

Let $\Omega = [0,1]^d$ be the unit cube in $\mathbb{R}^d$. We study the problem of how efficiently, in terms of the number of parameters, deep neural networks with the ReLU activation function can approximate functions in the Sobolev spaces…

Machine Learning · Statistics 2024-04-09 Jonathan W. Siegel