mlsanityData to 14 Oct 2026

Spiking neural networks for nonlinear regression

arXiv 2210.03515 ↗First posted 6 Oct 2022cs.NE cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Spiking neural networks, also often referred to as the third generation of neural networks, carry the potential for a massive reduction in memory and energy consumption over traditional, second-generation neural networks. Inspired by the undisputed efficiency of the human brain, they introduce temporal and neuronal sparsity, which can be exploited by next-generation neuromorphic hardware. To open the pathway toward engineering applications, we introduce this exciting technology in the context of continuum mechanics. However, the nature of spiking neural networks poses a challenge for regression problems, which frequently arise in the modeling of engineering sciences. To overcome this problem, a framework for regression using spiking neural networks is proposed. In particular, a network topology for decoding binary spike trains to real numbers is introduced, utilizing the membrane potential of spiking neurons. As the aim of this contribution is a concise introduction to this new methodology, several different spiking neural architectures, ranging from simple spiking feed-forward to complex spiking long short-term memory neural networks, are derived. Several numerical experiments directed towards regression of linear and nonlinear, history-dependent material models are carried out. A direct comparison with counterparts of traditional neural networks shows that the proposed framework is much more efficient while retaining precision and generalizability. All code has been made publicly available in the interest of reproducibility and to promote continued enhancement in this new domain.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 39 of its 123 references that are in the map. First posted on arXiv 6 Oct 2022.

Builds on

39 of 123 references.

References · 39

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  3. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  4. 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 473
  5. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
  6. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  7. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 266
  8. 2018Deep Learning in Spiking Neural Networkscited by 263
  9. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 259
  10. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 182
  11. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
  12. 2021Efficient Neuromorphic Signal Processing with Loihi 2cited by 96
27 more
  1. 2021The Modern Mathematics of Deep Learningcited by 63
  2. 2015Memory and information processing in neuromorphic systemscited by 48
  3. 2020Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacturecited by 48
  4. 2020Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networkscited by 47
  5. 2021Physics informed neural networks for continuum micromechanicscited by 46
  6. 2020Event-Based Angular Velocity Regression with Spiking Networkscited by 41
  7. 2021Sparse Spiking Gradient Descentcited by 41
  8. 2020Physics-Informed Neural Networks for Nonhomogeneous Material Identification in Elasticity Imagingcited by 40
  9. 2019Optimizing the energy consumption of spiking neural networks for neuromorphic applicationscited by 37
  10. 2017Reconstruction of three-dimensional porous media using generative adversarial neural networkscited by 36
  11. 2022ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescalescited by 35
  12. 2020Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applicationscited by 34
  13. 2021A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardwarecited by 32
  14. 2022NN-EUCLID: deep-learning hyperelasticity without stress datacited by 30
  15. 2020Meshless physics-informed deep learning method for three-dimensional solid mechanicscited by 27
  16. 2021A Spiking Neural Network for Image Segmentationcited by 27
  17. 2020A machine learning based plasticity model using proper orthogonal decompositioncited by 26
  18. 2018Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networkscited by 25
  19. 2021StereoSpike: Depth Learning with a Spiking Neural Networkcited by 21
  20. 2021Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)cited by 18
  21. 2022Spiking Neural Networks for Frame-based and Event-based Single Object Localizationcited by 18
  22. 2020Microstructure Generation via Generative Adversarial Network for Heterogeneous, Topologically Complex 3D Materialscited by 12
  23. 2021What machine learning can do for computational solid mechanicscited by 12
  24. 2022Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanicscited by 11
  25. 2021Interval and fuzzy physics-informed neural networks for uncertain fieldscited by 9
  26. 2022Spiking Neural Operators for Scientific Machine Learningcited by 8
  27. 2021A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructurescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 4; 2026: 1.

10 papers.

  1. 2023Deep Learning in Deterministic Computational Mechanicscited by 21
  2. 2024Autonomous Driving with Spiking Neural Networkscited by 13
  3. 2023Learning solution of nonlinear constitutive material models using physics-informed neural networks: COMM-PINNcited by 6
  4. 2025Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Timecited by 4
  5. 2024Hybrid variable spiking graph neural networks for energy-efficient scientific machine learningcited by 3
  6. 2025Underwater Image Enhancement by Convolutional Spiking Neural Networkscited by 3
  7. 2024SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networkscited by 2
  8. 2025Hardware-aware vs. Hardware-agnostic Energy Estimation for SNN in Space Applicationscited by 1
  9. 2025Neural Network Modeling of Microstructure Complexity Using Digital Librariescited by 0
  10. 2026Neuromorphic Parameter Estimation for Power Converter Health Monitoring Using Spiking Neural Networkscited by 0