paper-with-me

홈 › Papers

Variations on the Chebyshev-Lagrange Activation Function

2019-06-24 · Yuchen Li, Frank Rudzicz, Jekaterina Novikova

We seek to improve the data efficiency of neural networks and present novel implementations of parameterized piece-wise polynomial activation functions. The parameters are the y-coordinates of n+1 Chebyshev nodes per hidden unit and Lagrangian interpolation between the nodes produces the polynomial on [-1, 1]. We show results for different methods of handling inputs outside [-1, 1] on synthetic datasets, finding significant improvements in capacity of expression and accuracy of interpolation in models that compute some form of linear extrapolation from either ends. We demonstrate competitive or state-of-the-art performance on the classification of images (MNIST and CIFAR-10) and minimally-correlated vectors (DementiaBank) when we replace ReLU or tanh with linearly extrapolated Chebyshev-Lagrange activations in deep residual architectures.

📄 PDF Abstract BibTeX arXiv:1906.10064

Code (2)

jloveric/high-order-layers-torch pytorch
ychnlgy/Chebyshev-Lagrange pytorch

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

chebgreen: Learning and Interpolating Continuous Empirical Green's Functions from Data

2025-01-30 · Harshwardhan Praveen, Jacob Brown, Christopher Earls

In this work, we present a mesh-independent, data-driven library, chebgreen, to mathematically model one-dimensional systems, possessing an associated control parameter, and whose governing partial differential equation …

PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets

2024-10-14 · Ali Kashefi

Kolmogorov-Arnold Networks (KANs) have recently gained attention as an alternative to traditional Multilayer Perceptrons (MLPs) in deep learning frameworks. KANs have been integrated into various deep learning architectu…

3D Classification3D Object Classification3D Point Cloud ClassificationKolmogorov-Arnold Networks+1

Deterministic Reservoir Computing for Chaotic Time Series Prediction

2025-01-26 · Johannes Viehweg, Constanze Poll, Patrick Mäder

Reservoir Computing was shown in recent years to be useful as efficient to learn networks in the field of time series tasks. Their randomized initialization, a computational benefit, results in drawbacks in theoretical a…

PredictionTime SeriesTime Series ForecastingTime Series Prediction

Physics-Informed Chebyshev Polynomial Neural Operator for Parametric Partial Differential Equations

2026-02-02 · Biao Chen, Jing Wang, Hairun Xie, Qineng Wang 외 arxiv

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 per…

Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions

2023-12-21 · Juncai He, Jinchao Xu

In this study, we establish that deep neural networks employing ReLU and ReLU$^2$ activation functions can effectively represent Lagrange finite element functions of any order on various simplicial meshes in arbitrary di…