通过紧密的激发-抑制平衡在浅尖反复神经网络中实现最佳准确性和稳健性
Shiwen Li1,2,3, Junsong Wang1,2,4, Syeda Shamaila Zareen1
1School of Artificial Intelligence, Shenzhen Technology University, Shenzhen 518118, P. R. China.
International journal of neural systems
|February 23, 2026
概括
我们引入了一种激发抑制平衡的浅层尖端循环神经网络 (EI-SRNN),提高了准确性和稳定性. 这种生物启发的模型实现了低计算复杂度的最佳性能,克服了传统的权衡.
科学领域:
- 计算神经科学是一种神经科学.
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 传统的深度神经网络 (DNN) 面临着高计算复杂性和缺乏生物解释性的挑战.
- 尖端循环神经网络 (SRNN) 在使用离散尖端事件处理时空数据时提供生物可信性和效率.
研究的目的:
- 提出和评估一个激发抑制平衡的浅层SRNN (EI-SRNN),以提高性能.
- 研究平衡激发和抑制对SRNN准确性,稳定性和计算复杂性的影响.
主要方法:
- 通过优化储存神经元输入电流来开发EI-SRNN,以实现紧密平衡的状态,灵感来自大脑神经动力学.
- 分析了EI-SRNN的神经编码能力和信息记忆能力.
- 在不同程度的激发和抑制下比较模型性能.
主要成果:
- EI-SRNN实现了低计算复杂度的最佳准确性,挑战了准确性-稳定性权衡.
- 紧密平衡的兴奋和抑制状态导致了更高的神经编码和记忆能力.
- 当储库被激发主导时,与抑制相比,性能下降的速度更快.
结论:
- 通过利用平衡的激发和抑制,EI-SRNN表现出卓越的准确性和稳定性.
- 为平衡状态进行优化可以增强SRNN中神经编码和记忆能力.
- EI-SRNN为传统的DNN提供了一个生物学上可信和计算效率高的替代方案.
相关概念视频
The Role of Ion Channels in Neuronal Computation
4.0K
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....
4.0K
Neural Regulation
43.6K
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.
43.6K
Long-term Potentiation
3.7K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when...
Hebbian LTP
LTP can occur when...
3.7K
Long-term Potentiation
58.9K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
58.9K
Neural Circuits
3.0K
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...
3.0K


