Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

89
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
89
Neural Regulation01:37

Neural Regulation

39.4K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.4K
The Role of Ion Channels in Neuronal Computation01:19

The Role of Ion Channels in Neuronal Computation

3.2K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.2K
Residual Plots01:07

Residual Plots

4.6K
A residual plot is a statistical representation of data used to analyze correlation and regression results. It helps verify the requirements for drawing specific conclusions about correlation and regression. To obtain the residual plot, first, the residual for each data value is calculated, which is simply the vertical distance between the observed and the predicted value obtained from the regression equation.
When the residual values are plotted against the variable x, it is called a residual...
4.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Neuromorphic spike-based large language model.

National science review·2026
Same author

Dynamic spatio-temporal pruning for efficient spiking neural networks.

Frontiers in neuroscience·2025
Same author

Neuromorphic neuromodulation: Towards the next generation of closed-loop neurostimulation.

PNAS nexus·2024
Same author

Neuromorphic intermediate representation: A unified instruction set for interoperable brain-inspired computing.

Nature communications·2024
Same author

Modeling and hardware implementation of universal interface-based floating fractional-order mem-elements.

Chaos (Woodbury, N.Y.)·2023
Same author

Weak self-supervised learning for seizure forecasting: a feasibility study.

Royal Society open science·2022

Related Experiment Video

Updated: Jun 27, 2025

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
07:34

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

9.9K

Spiking neural networks for nonlinear regression.

Alexander Henkes1,2, Jason K Eshraghian3, Henning Wessels2

  • 1Computational Mechanics Group, ETH Zurich, Zurich, Switzerland.

Royal Society Open Science
|May 3, 2024
PubMed
Summary

Spiking neural networks (SNNs) offer significant energy and memory savings for engineering tasks like structural health monitoring. This study introduces novel SNN architectures for accurate and efficient regression, decoding spike trains to real numbers.

Keywords:
artificial neural networksneuromorphic computingregressionspiking neural networks

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K
Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
05:19

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

7.0K

Related Experiment Videos

Last Updated: Jun 27, 2025

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
07:34

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

9.9K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K
Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
05:19

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

7.0K

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Materials Science

Background:

  • Spiking neural networks (SNNs), the third generation of neural networks, promise reduced energy and memory consumption compared to traditional networks.
  • Their brain-inspired temporal and neuronal sparsity is ideal for neuromorphic hardware.
  • Energy efficiency is critical for engineering applications, particularly in data-driven mechanics and structural health monitoring.

Purpose of the Study:

  • To present a novel formulation for the accuracy and energy efficiency of SNNs in regression tasks.
  • To introduce a network topology for decoding binary spike trains into real numbers using membrane potential.
  • To derive various SNN architectures, from feed-forward to Long Short-Term Memory (LSTM) networks, optimized for energy efficiency.

Main Methods:

  • Developed a novel network topology for decoding spike trains to real numbers.
  • Formulated and derived several SNN architectures, including spiking feed-forward and spiking LSTM networks.
  • Ensured architectures avoid dense layers to maximize SNN energy efficiency benefits.

Main Results:

  • Demonstrated the accuracy of the proposed SNN architectures through numerical examples involving diverse material models.
  • Validated performance on linear, nonlinear, and history-dependent material models.
  • Achieved high accuracy while maintaining the inherent energy efficiency of SNNs.

Conclusions:

  • The proposed SNN architectures provide an accurate and highly energy-efficient solution for regression tasks in engineering.
  • The novel decoding method and dense-layer-free architectures unlock the full potential of SNNs for neuromorphic hardware.
  • The framework is adaptable for regressing custom functions beyond the mechanical examples presented.