p-adic cellular neural networks: applications to image processing
From MaRDI portal
Publication:2688082
DOI10.1016/J.PHYSD.2023.133668zbMATH Open1506.68027arXiv2210.14132OpenAlexW4318384244MaRDI QIDQ2688082FDOQ2688082
W. A. Zúñiga-Galindo, B. A. Zambrano-Luna
Publication date: 9 March 2023
Published in: Physica D (Search for Journal in Brave)
Abstract: The p-adic cellular neural networks (CNNs) are mathematical generalizations of the neural networks introduced by Chua and Yang in the 80s. In this work we present two new types of CNNs that can perform computations with real data, and whose dynamics can be understood almost completely. The first type of networks are edge detectors for grayscale images. The stationary states of these networks are organized hierarchically in a lattice structure. The dynamics of any of these networks consists of transitions toward some minimal state in the lattice. The second type is a new class of reaction-diffusion networks. We investigate the stability of these networks and show that they can be used as filters to reduce noise, preserving the edges, in grayscale images polluted with additive Gaussian noise. The networks introduced here were found experimentally. They are abstract evolution equations on spaces of real-valued functions defined in the p-adic unit ball for some prime number p. In practical applications the prime p is determined by the size of image, and thus, only small primes are used. We provide several numerical simulations showing how these networks work.
Full work available at URL: https://arxiv.org/abs/2210.14132
Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10) Networks and circuits as models of computation; circuit complexity (68Q06)
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Pseudo-differential equations and stochastics over non-Archimedean fields
- Cellular neural networks: theory
- p-adic models of ultrametric diffusion constrained by hierarchical energy landscapes
- p-adic description of characteristic relaxation in complex systems
- On \(p\)-adic mathematical physics
- Fourier Analysis on Local Fields. (MN-15)
- Geometric partial differential equations and image analysis
- Pseudodifferential equations over non-Archimedean spaces
- Ultrametric Pseudodifferential Equations and Applications
- Ultrametric diffusion, exponential landscapes, and the first passage time problem
- Mathematical image processing. Translated from the German
- Compression of images with the use of representations by \(p\)-adic mappings and approximations by Mahler polynomials
- Segmentation of images in \(p\)-adic and Euclidean metrics.
- Non-Archimedean pseudodifferential operators and Feller semigroups
- Regularization of \(p\)-adic string amplitudes, and multivariate local zeta functions
- Non-Archimedean reaction-ultradiffusion equations and complex hierarchic systems
- \(p\)-adic analogue of the porous medium equation
- An Introduction to the Theory of Local Zeta Functions from Scratch
Cited In (6)
- Feynman formulas for \(qp\)- and \(pq\)-quantization of some Vladimirov type time-dependent Hamiltonians on finite adeles
- Some further classes of pseudo-differential operators in the \(p\)-adic context and their applications
- Hierarchical neural networks, \(p\)-adic PDEs, and applications to image processing
- The Vladimirov operator with variable coefficients on finite adeles and the Feynman formulas for the Schrödinger equation
- Cellular Neural Networks Proposed for Image Predictive Coding
- An aperiodically intermittent control for finite-time and fixed-time synchronization of stochastic FCNN with switching parameters
Uses Software
Recommendations
- Image-processing algorithms realized by discrete-time cellular neural networks and their circuit implementations 👍 👎
- ADVANCED IMAGE PROCESSING CELLULAR NEURAL NETWORKS 👍 👎
- Image processing with a cellular nonlinear network 👍 👎
- P-ADIC DYNAMICAL SYSTEMS AND NEURAL NETWORKS 👍 👎
- Image processing using cellular neural networks based on multi-valued and universal binary neurons 👍 👎
- CELLULAR NEURAL NETWORKS AND VISUAL COMPUTING 👍 👎
- \(p\)-adic cellular neural networks 👍 👎
- Cellular Neural Networks Proposed for Image Predictive Coding 👍 👎
- Neural network coding of natural images with applications to pure mathematics 👍 👎
This page was built for publication: \(p\)-adic cellular neural networks: applications to image processing
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2688082)
