Chebyshev Feature Neural Network for Accurate Function Approximation
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 the first hidden layer, followed by the standard fully connected hidden layers. The learnable frequencies of the Chebyshev layer are initialized with exponential distributions to cover a wide range of frequencies. Combined with a multi-stage training strategy, we demonstrate that this CFNN structure can achieve machine accuracy during training. A comprehensive set of numerical examples for dimensions up to $20$ are provided to demonstrate the effectiveness and scalability of the method.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximation
Accurate approximation of complex nonlinear functions is a fundamental challenge across many scientific and engineering domains. Traditional neural network architectures, such as Multi-Layer Perceptrons (MLPs), often str…
Kolmogorov-Arnold NetworksBeyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
The performance of Deep Q-Networks (DQN) is critically dependent on the ability of its underlying neural network to accurately approximate the action-value function. Standard function approximators, such as multi-layer p…
Reinforcement LearningA Novel Online Pseudospectral Method for Approximation of Nonlinear Systems Dynamics
This paper presents a novel online system identification approach utilizing the Chebyshev pseudospectral (PS) method to approximate the dynamics of a continuous-time nonlinear system. Unlike conventional periodic samplin…
State EstimationConvolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited
Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet b…
GPRGraph LearningNode ClassificationIterative Polynomial Approximation Algorithms for Inverse Graph Filters
Chebyshev interpolation polynomials exhibit the exponential approximation property to analytic functions on a cube. Based on the Chebyshev interpolation polynomial approximation, we propose iterative polynomial approxima…