一个多突触尖端神经元,用于同时编码时空动态
Liangwei Fan1, Hui Shen2, Xiangkai Lian1
1College of Intelligence Science and Technology, National University of Defense Technology, Changsha, Hunan, China.
Nature communications
|August 4, 2025
概括
一个新的多突触发射 (MSF) 神经元增强尖端神经网络 (SNN) 以更好的时空数据处理. 在神经模拟计算任务中,MSF神经元提高了准确性和效率.
科学领域:
- 神经形态计算是一种神经形态计算.
- 计算神经科学是一种计算神经科学.
- 人工智能的人工智能是人工智能.
背景情况:
- 尖端神经网络 (SNN) 提供了由于时间动态的生物可信性和计算能力.
- 标准的SNN神经元在同时编码复杂的时空输入动态方面面临着挑战.
研究的目的:
- 介绍多突触发射 (MSF) 神经元,灵感来自生物多突触连接.
- 使SNN能够共同编码空间强度和时间动态,以提高性能.
主要方法:
- 提出MSF神经元模型,在一个后突触神经元上具有多个突触和不同的值.
- 导出替代梯度的最佳值选择和参数优化.
- 在各种基准上实施和评估基于MSF的深度SNN.
主要成果:
- 无线医生神经元将泄漏的整合和火 (LIF) 和ReLU神经元泛化.
- 与LIF神经元相比,实现更高的精度,同时保持低功耗和延迟.
- 在事件驱动任务中超过ReLU神经元,显示出高执行效率.
结论:
- 无线神经元显著提升了神经形态计算能力.
- 启用可扩展的深度SNN,用于现实世界的时空应用,而不会损失性能.
相关概念视频
The Role of Ion Channels in Neuronal Computation
3.3K
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....
3.3K
The Synapse
127.4K
Neurons communicate with one another by passing on their electrical signals to other neurons. A synapse is the location where two neurons meet to exchange signals. At the synapse, the neuron that sends the signal is called the presynaptic cell, while the neuron that receives the message is called the postsynaptic cell. Note that most neurons can be both presynaptic and postsynaptic, as they both transmit and receive information.
127.4K
Integration of Synaptic Events
2.2K
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...
2.2K
Neural Circuits
1.6K
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...
1.6K
Synaptic Signaling
76.0K
Neurons communicate at synapses, or junctions, to excite or inhibit the activity of other neurons or target cells, such as muscles. Synapses may be chemical or electrical.
76.0K
Neuronal Communication
1.4K
Neurons, the fundamental units of the brain and nervous system, communicate through complex electrochemical signals that underpin all cognitive and bodily functions. This communication is primarily facilitated by a process involving the generation and propagation of an action potential along the axon of the neuron. When the internal electrical charge of a neuron surpasses a certain threshold, an action potential is triggered. This rapid change in voltage travels swiftly along the axon to the...
1.4K


