Related Experiment Video
Updated: May 24, 2026
05:19
Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
Published on: November 12, 2019
Spiking Neural Membrane Systems with Temporal Coding
Jianbin Yan1, Zhihui Shu1, Hong Peng1
1School of Computer and Software Engineering, Xihua University, Chengdu 610039, P. R. China.
International Journal of Neural Systems
|May 23, 2026
Summary
This study introduces a novel TC-SNP neuron model for Spiking Neural P Systems, enhancing temporal coding and achieving a balance between accuracy and low latency in image classification tasks.
Area of Science:
- Computational Neuroscience
- Membrane Computing
- Artificial Intelligence
Background:
- Spiking neural P systems (SNP systems) are neuromorphic models inspired by neuron spiking.
- Nonlinear spiking neural P systems (NSNP systems) are a nonlinear variant.
- Existing spiking neural networks often use fixed reset methods, limiting temporal encoding.
Purpose of the Study:
- To propose a novel spiking neuron model, TC-SNP neurons, based on NSNP systems.
- To enhance the temporal encoding capabilities of spiking neural models.
- To improve accuracy and reduce latency in image classification tasks.
Main Methods:
- Developed the TC-SNP neuron model, a temporal coding variant of NSNP systems.
- Introduced a dynamic membrane potential reset mechanism for nonlinear regulation.
- Implemented the model within deep learning architectures for image classification.
Main Results:
- The TC-SNP model demonstrated enhanced temporal encoding capabilities.
- Achieved a balance between high accuracy and low latency.
- Significantly improved classification accuracy on CIFAR-10, CIFAR-100, and TinyImageNet datasets compared to state-of-the-art models.
Conclusions:
- The proposed TC-SNP model offers a practical and effective variant of Spiking Neural Networks.
- Dynamic reset mechanisms enhance neuron temporal encoding, leading to superior performance.
- The model shows promise for advanced neuromorphic computing applications, particularly in image recognition.
Related Concept Videos
01:28Integration of Synaptic Events
Synaptic integration mainly includes the summation of graded potentials. Graded potentials, regardless of their type, cause subtle alterations in membrane voltage, resulting in either depolarization or hyperpolarization. These incremental changes, when combined or summed, can propel the neuron toward its threshold. Consider, for example, a membrane experiencing a +15 mV shift, causing it to depolarize from -70 mV to -55 mV. In this scenario, graded potentials govern the membrane's ability to...
01:19The Role of Ion Channels in Neuronal Computation
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.
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.