Optimizing Basis Function Selection in Constructive Wavelet Neural Networks and Its Applications

• URL: http://arxiv.org/abs/2507.09213v1
• Date: Sat, 12 Jul 2025 09:09:26 GMT
• Title: Optimizing Basis Function Selection in Constructive Wavelet Neural Networks and Its Applications
• Authors: Dunsheng Huang, Dong Shen, Lei Lu, Ying Tan,
• Abstract summary: This study introduces a constructive wavelet neural network (WNN) that selects initial bases and trains functions.<n>We analyze the frequency of unknown nonlinear functions and select appropriate initial wavelets based on their primary frequency components.<n>This leads to a novel constructive framework consisting of a frequency estimator and a wavelet-basis increase mechanism to prioritize high-energy bases.
• Score: 17.97897706297086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Wavelet neural network (WNN), which learns an unknown nonlinear mapping from the data, has been widely used in signal processing, and time-series analysis. However, challenges in constructing accurate wavelet bases and high computational costs limit their application. This study introduces a constructive WNN that selects initial bases and trains functions by introducing new bases for predefined accuracy while reducing computational costs. For the first time, we analyze the frequency of unknown nonlinear functions and select appropriate initial wavelets based on their primary frequency components by estimating the energy of the spatial frequency component. This leads to a novel constructive framework consisting of a frequency estimator and a wavelet-basis increase mechanism to prioritize high-energy bases, significantly improving computational efficiency. The theoretical foundation defines the necessary time-frequency range for high-dimensional wavelets at a given accuracy. The framework's versatility is demonstrated through four examples: estimating unknown static mappings from offline data, combining two offline datasets, identifying time-varying mappings from time-series data, and capturing nonlinear dependencies in real time-series data. These examples showcase the framework's broad applicability and practicality. All the code will be released at https://github.com/dshuangdd/CWNN.

Related papers

• Learning from Scratch: Structurally-masked Transformer for Next Generation Lib-free Simulation [3.7467132954493536]
  This paper proposes a neural framework for power and timing prediction of multi-stage data path.<n>To the best of our knowledge, this is the first language-based, netlist-aware neural network designed explicitly for standard cells.
  arXiv  Detail & Related papers  (2025-07-23T10:46:25Z)
• Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons [69.73249913506042]
  This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons to process time-domain signals directly.<n>By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity.<n> Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs.
  arXiv  Detail & Related papers  (2025-06-24T21:14:59Z)
• ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data [59.78770412981611]
  In real-world applications, most nodes may not possess any available temporal data during training.<n>We propose a principled framework named ST-FiT to handle this problem.
  arXiv  Detail & Related papers  (2024-12-14T17:51:29Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems [20.006163951844357]
  We propose a simulation-free framework for training neural ordinary differential equations (NODEs) We employ the Fourier analysis to estimate temporal and potential high-order spatial gradients from noisy observational data. Our approach outperforms state-of-the-art methods in terms of training time, dynamics prediction, and robustness.
  arXiv  Detail & Related papers  (2024-05-19T13:15:23Z)
• Machine learning for phase-resolved reconstruction of nonlinear ocean wave surface elevations from sparse remote sensing data [37.69303106863453]
  We propose a novel approach for phase-resolved wave surface reconstruction using neural networks. Our approach utilizes synthetic yet highly realistic training data on uniform one-dimensional grids.
  arXiv  Detail & Related papers  (2023-05-18T12:30:26Z)
• Fast Temporal Wavelet Graph Neural Networks [7.477634824955323]
  We propose Fast Temporal Wavelet Graph Neural Networks (FTWGNN) for learning tasks on timeseries data. We employ Multiresolution Matrix Factorization (MMF) to factorize the highly dense graph structure and compute the corresponding sparse wavelet basis. Experimental results on real-world PEMS-BAY, METR-LA traffic datasets and AJILE12 ECoG dataset show that FTWGNN is competitive with the state-of-the-arts.
  arXiv  Detail & Related papers  (2023-02-17T01:21:45Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
  This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
  arXiv  Detail & Related papers  (2022-09-29T04:06:00Z)
• RF-Photonic Deep Learning Processor with Shannon-Limited Data Movement [0.0]
  Optical neural networks (ONNs) are promising accelerators with ultra-low latency and energy consumption. We introduce our multiplicative analog frequency transform ONN (MAFT-ONN) that encodes the data in the frequency domain. We experimentally demonstrate the first hardware accelerator that computes fully-analog deep learning on raw RF signals.
  arXiv  Detail & Related papers  (2022-07-08T16:37:13Z)
• Learning Wave Propagation with Attention-Based Convolutional Recurrent Autoencoder Net [0.0]
  We present an end-to-end attention-based convolutional recurrent autoencoder (AB-CRAN) network for data-driven modeling of wave propagation phenomena. We employ a denoising-based convolutional autoencoder from the full-order snapshots given by time-dependent hyperbolic partial differential equations for wave propagation. The attention-based sequence-to-sequence network increases the time-horizon of prediction by five times compared to the plain RNN-LSTM.
  arXiv  Detail & Related papers  (2022-01-17T20:51:59Z)
• Wave-based extreme deep learning based on non-linear time-Floquet entanglement [0.7614628596146599]
  Complex neuromorphic computing tasks, which require strong non-linearities, have so far remained out-of-reach of wave-based solutions. Here, we demonstrate the relevance of Time-Floquet physics to induce a strong non-linear entanglement between signal inputs at different frequencies. We prove the efficiency of the method for extreme learning machines and reservoir computing to solve a range of challenging learning tasks.
  arXiv  Detail & Related papers  (2021-07-19T00:18:09Z)
• Spatio-Temporal Graph Scattering Transform [54.52797775999124]
  Graph neural networks may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data. We put forth a novel mathematically designed framework to analyze-temporal data.
  arXiv  Detail & Related papers  (2020-12-06T19:49:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.