English
Related papers

Related papers: Variations on the Chebyshev-Lagrange Activation Fu…

200 papers

Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks. However, the benefits of novel activation functions have been inconsistent and task dependent, and…

Machine Learning · Computer Science 2022-01-25 Garrett Bingham , Risto Miikkulainen

Approximation theorem is one of the most important aspects of numerical analysis that has evolved over the years with many different approaches. Some of the most popular approximation methods include the Lebesgue approximation theorem, the…

Numerical Analysis · Mathematics 2024-04-16 Ishmael N. Amartey

Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and…

Computer Vision and Pattern Recognition · Computer Science 2017-09-07 Dongyoon Han , Jiwhan Kim , Junmo Kim

Deep neural networks have recently been recognized as one of the powerful learning techniques in computer vision and medical image analysis. Trained deep neural networks need to be generalizable to new data that was not seen before. In…

Machine Learning · Computer Science 2020-10-07 Shih-Gu Huang , Moo K. Chung , Anqi Qiu , Alzheimer's Disease Neuroimaging Initiative

We present a new Deep Neural Network (DNN) architecture capable of approximating functions up to machine accuracy. Termed Chebyshev Feature Neural Network (CFNN), the new structure employs Chebyshev functions with learnable frequencies as…

Machine Learning · Computer Science 2024-12-24 Zhongshu Xu , Yuan Chen , Dongbin Xiu

We study neural networks with trainable low-degree rational activation functions and show that they are more expressive and parameter-efficient than modern piecewise-linear and smooth activations such as ELU, LeakyReLU, LogSigmoid, PReLU,…

Machine Learning · Computer Science 2026-02-16 Maosen Tang , Alex Townsend

The algebraic polynomial interpolation on uniformly distributed nodes is affected by the Runge phenomenon, also when the function to be interpolated is analytic. Among all techniques that have been proposed to defeat this phenomenon, there…

Numerical Analysis · Mathematics 2014-07-10 Stefano De Marchi , Francesco Dell'Accio , Mariarosa Mazza

We derive a stronger uniqueness result if a function with compact support and its truncated Hilbert transform are known on the same interval by using the Sokhotski-Plemelj formulas. To find a function from its truncated Hilbert transform,…

Machine Learning · Computer Science 2020-02-13 Jason You

In this article, we study bivariate polynomial interpolation on the node points of degenerate Lissajous figures. These node points form Chebyshev lattices of rank $1$ and are generalizations of the well-known Padua points. We show that…

Numerical Analysis · Mathematics 2016-04-05 Wolfgang Erb

Neural operators have emerged as powerful deep learning frameworks for approximating solution operators of parameterized partial differential equations (PDE). However, current methods predominantly rely on multilayer perceptrons (MLPs) for…

Fluid Dynamics · Physics 2026-02-03 Biao Chen , Jing Wang , Hairun Xie , Qineng Wang , Shuai Zhang , Yifan Xia , Jifa Zhang

Training large deep neural networks is resource intensive. This study investigates whether Lyapunov exponents can accelerate this process by aiding in the selection of hyperparameters. To study this I formulate an optimization problem using…

Machine Learning · Computer Science 2024-10-10 Tirthankar Mittra

Lung cancer remains one of the leading causes of cancer-related mortality worldwide, with early and accurate diagnosis playing a pivotal role in improving patient outcomes. Automated detection of pulmonary nodules in computed tomography…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Abhinav Roy , Bhavesh Gyanchandani , Aditya Oza

In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Idan Kligvasser , Tamar Rott Shaham , Tomer Michaeli

This work presents an adaptive activation method for neural networks that exploits the interdependency of features. Each pixel, node, and layer is assigned with a polynomial activation function, whose coefficients are provided by an…

Computer Vision and Pattern Recognition · Computer Science 2018-11-22 Jinhyeok Jang , Jaehong Kim , Jaeyeon Lee , Seungjoon Yang

Implicit neural representations (INRs) are a powerful paradigm for modeling data, offering a continuous alternative to discrete signal representations. Their ability to compactly encode complex signals has led to strong performance in many…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Pandula Thennakoon , Avishka Ranasinghe , Mario De Silva , Buwaneka Epakanda , Roshan Godaliyadda , Parakrama Ekanayake , Vijitha Herath

Successive linear transforms followed by nonlinear "activation" functions can approximate nonlinear functions to arbitrary precision given sufficient layers. The number of necessary layers is dependent on, in part, by the nature of the…

Neural and Evolutionary Computing · Computer Science 2018-09-26 Andrei Nicolae

We study the interpolation power of deep ReLU neural networks. Specifically, we consider the question of how efficiently, in terms of the number of parameters, deep ReLU networks can interpolate values at $N$ datapoints in the unit ball…

Machine Learning · Computer Science 2025-08-27 Jonathan W. Siegel

Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers.…

Machine Learning · Computer Science 2024-02-20 Chinmay Rane , Kanishka Tyagi , Michael Manry

For a function that is analytic on and around an interval, Chebyshev polynomial interpolation provides spectral convergence. However, if the function has a singularity close to the interval, the rate of convergence is near one. In these…

Numerical Analysis · Mathematics 2017-08-10 Kevin W. Aiton , Tobin A. Driscoll

Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research. Loss functions are a type of metaknowledge that is crucial to effective training of DNNs, however, their…

Machine Learning · Computer Science 2020-10-05 Santiago Gonzalez , Risto Miikkulainen