沿道区域整合和多次发射神经元:改善尖端神经网络的时空学习
IEEE transactions on neural networks and learning systems
|September 11, 2025
概括
本研究介绍了通道区域整合和多次发射 (CRIMF) 神经元,以增强尖端神经网络 (SNN) 以获得卓越的时空学习和能源效率. CRIMF神经元克服了记忆的局限性,梯度问题和网络退化,在复杂的任务上表现优于现有的方法.
科学领域:
- 人工智能的人工智能
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
背景情况:
- 尖端神经网络 (SNN) 提供节能,以事件驱动的计算,具有高的生物可信性.
- 现有的SNN与长期记忆,网络退化,梯度和异质学习作斗争,限制了它们的时空学习能力.
- 目前的评估往往侧重于简单的任务,未能在复杂的时空学习中展示SNN的全部潜力.
研究的目的:
- 引入一种新的神经元模型,即通道区域整合和多次发射 (CRIMF) 神经元,以提高SNN在时空学习中的性能.
- 解决现有SNN的关键局限性,包括长期记忆缺陷,网络退化,梯度和和异质学习中的挑战.
- 证明CRIMF神经元在现实世界时空任务中的有效性,特别是从EEG数据中识别情绪.
主要方法:
- 提出了具有区域当前内部状态的CRIMF神经元,以改善记忆和长期时间信息处理.
- 在CRIMF神经元内实施多个触发机制,通过调整膜电位动力学来减轻低活性和梯度和.
- 引入了针对特定时间特征学习的道式学习策略,并采用了针对特定时间特征学习的差异化度指数,并采用了特定的重置和正常化方程来防止网络退化.
主要成果:
- 与最先进的方法相比,基于CRIMF的SNNs在静态时间任务上表现出更高的性能.
- 在动态时间任务上,CRIMF神经元的表现优于先进的尖端神经元和人工神经网络的反复单元.
- 对情绪脑电图 (EEG) 数据集的评估,使用手动功能和原始信号,证实了CRIMF方法在准确性和低能耗方面的有效性.
结论:
- CRIMF神经元模型显著提高了SNN的时空学习能力.
- CRIMF神经元有效地解决了SNN中的关键限制,为更强大,更有效的神经形态计算铺平了道路.
- 拟议的基于CRIMF的SNNs对复杂的现实应用非常有前途,特别是在处理动态时间数据 (如EEG信号) 时,能耗降低.
相关概念视频
Integration of Synaptic Events
3.5K
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...
3.5K
The Role of Ion Channels in Neuronal Computation
3.7K
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....
3.7K
Neural Circuits
2.7K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.7K
Propagation of Action Potentials
9.0K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
9.0K


