Relay-Assisted Activation-Integrated SIM for Wireless Physical Neural Networks

• URL: http://arxiv.org/abs/2604.04212v1
• Date: Sun, 05 Apr 2026 18:07:13 GMT
• Title: Relay-Assisted Activation-Integrated SIM for Wireless Physical Neural Networks
• Abstract summary: Wireless physical neural networks (WPNNs) have emerged as a promising paradigm for performing neural computation directly in the physical layer of wireless systems.<n>We propose a relay-assisted WPNN architecture based on activation-integrated stacked intelligent metasurfaces (AI-SIMs)
• Score: 53.64687377045908
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Wireless physical neural networks (WPNNs) have emerged as a promising paradigm for performing neural computation directly in the physical layer of wireless systems, offering low latency and high energy efficiency. However, most existing WPNN implementations primarily rely on linear physical transformations, which fundamentally limits their expressiveness. In this work, we propose a relay-assisted WPNN architecture based on activation-integrated stacked intelligent metasurfaces (AI-SIMs), where each passive metasurface layer enabling linear wave manipulation is cascaded with an activation metasurface layer that realizes nonlinear processing in the analog domain. By deliberately structuring multi-hop wireless propagation, the relay amplification matrix and the metasurface phase-shift matrices jointly act as trainable network weights, while hardware-implemented activation functions provide essential nonlinearity. Simulation results demonstrate that the proposed architecture achieves high classification accuracy, and that incorporating hardware-based activation functions significantly improves representational capability and performance compared with purely linear physical implementations.

Related papers

• Multi-layer MIMO Relay as Deep Physical Neural Networks: Power Amplifiers as Activation Functions [56.870614369768354]
  Wireless physical neural networks (WPNNs) embed neural computation directly into analog hardware.<n>We propose a deep WPNN in which nonlinear activations are realized by a multi-hop multiple-input multiple-output (MIMO) relay network.<n>We show that the proposed architecture enables accurate over-the-air inference for image classification.
  arXiv  Detail & Related papers  (2026-07-20T09:45:07Z)
• Low-power analogue neural networks with trainable nonlinear connections for continuous control [54.59241649882409]
  Physical neural networks promise low-power machine learning by computing directly with analogue device physics.<n>We place trainable nonlinear functions on the connections, making each physical connection a learnable computational element.<n>We find that the benefit is task-dependent and follows from the smoothness of the physical basis.
  arXiv  Detail & Related papers  (2026-06-21T15:55:23Z)
• Optical Neural Networks from Coherent Transient Dynamics in Waveguide QED [0.0]
  Optical neural networks promise ultrafast, low-energy information processing by performing computation directly with photons.<n>We propose an all-optical fully connected neural network architecture in which the basic neuronal functions are realized by coherent quantum dynamics.<n>Full-physics simulations demonstrate high classification accuracy on MNIST and colored-object recognition tasks.
  arXiv  Detail & Related papers  (2026-05-18T02:11:34Z)
• Kirchhoff-Inspired Neural Networks for Evolving High-Order Perception [51.28469959548178]
  We propose the Kirchhoff-Inspired Neural Network (KINN), a state-variable-based network architecture constructed based on Kirchhoff's current law.<n>KINN derives numerically stable state updates from fundamental ordinary differential equations, enabling the explicit decoupling and encoding of higher-order evolutionary components.
  arXiv  Detail & Related papers  (2026-03-25T06:17:31Z)
• Personalized Spiking Neural Networks with Ferroelectric Synapses for EEG Signal Processing [4.084778152234208]
  We show that programmable ferroelectric hardware can support robust, low-overhead adaptation in spiking neural networks.<n>Results demonstrate that programmable ferroelectric hardware can support robust, low-overhead adaptation in spiking neural networks.
  arXiv  Detail & Related papers  (2025-12-22T01:09:24Z)
• Improved Physics-Driven Neural Network to Solve Inverse Scattering Problems [11.456980278006574]
  This paper presents an improved physics-driven neural network (IPDNN) framework for solving electromagnetic inverse scattering problems (ISPs)<n>A new Gaussian-localized oscillation-suppressing window (GLOW) activation function is introduced to stabilize convergence and enable a lightweight yet accurate network architecture.<n>The proposed solver achieves superior reconstruction accuracy, robustness, and efficiency compared with existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-10T05:41:09Z)
• Generative System Dynamics in Recurrent Neural Networks [56.958984970518564]
  We investigate the continuous time dynamics of Recurrent Neural Networks (RNNs)<n>We show that skew-symmetric weight matrices are fundamental to enable stable limit cycles in both linear and nonlinear configurations.<n> Numerical simulations showcase how nonlinear activation functions not only maintain limit cycles, but also enhance the numerical stability of the system integration process.
  arXiv  Detail & Related papers  (2025-04-16T10:39:43Z)
• Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systems [49.819436680336786]
  We propose an efficient transformed Gaussian process state-space model (ETGPSSM) for scalable and flexible modeling of high-dimensional, non-stationary dynamical systems.<n>Specifically, our ETGPSSM integrates a single shared GP with input-dependent normalizing flows, yielding an expressive implicit process prior that captures complex, non-stationary transition dynamics.<n>Our ETGPSSM outperforms existing GPSSMs and neural network-based SSMs in terms of computational efficiency and accuracy.
  arXiv  Detail & Related papers  (2025-03-24T03:19:45Z)
• Short-reach Optical Communications: A Real-world Task for Neuromorphic Hardware [42.043435071139434]
  Spiking neural networks (SNNs) emulated on dedicated neuromorphic accelerators promise to offer energy-efficient signal processing.<n>Here, we describe an intensity-modulation, direct-detection (IM/DD) task that is relevant to high-speed optical communication systems used in data centers.
  arXiv  Detail & Related papers  (2024-12-04T08:46:55Z)
• Equivariant Matrix Function Neural Networks [1.8717045355288808]
  We introduce Matrix Function Neural Networks (MFNs), a novel architecture that parameterizes non-local interactions through analytic matrix equivariant functions. MFNs is able to capture intricate non-local interactions in quantum systems, paving the way to new state-of-the-art force fields.
  arXiv  Detail & Related papers  (2023-10-16T14:17:00Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• On the Application of Data-Driven Deep Neural Networks in Linear and Nonlinear Structural Dynamics [28.979990729816638]
  The use of deep neural network (DNN) models as surrogates for linear and nonlinear structural dynamical systems is explored. The focus is on the development of efficient network architectures using fully-connected, sparsely-connected, and convolutional network layers. It is shown that the proposed DNNs can be used as effective and accurate surrogates for predicting linear and nonlinear dynamical responses under harmonic loadings.
  arXiv  Detail & Related papers  (2021-11-03T13:22:19Z)
• Training End-to-End Analog Neural Networks with Equilibrium Propagation [64.0476282000118]
  We introduce a principled method to train end-to-end analog neural networks by gradient descent. We show mathematically that a class of analog neural networks (called nonlinear resistive networks) are energy-based models. Our work can guide the development of a new generation of ultra-fast, compact and low-power neural networks supporting on-chip learning.
  arXiv  Detail & Related papers  (2020-06-02T23:38:35Z)

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.