分享漏洞整合和发射神经元,用于高效记忆的尖端神经网络
Youngeun Kim1, Yuhang Li1, Abhishek Moitra1
1Department of Electrical Engineering, Yale University, New Haven, CT, United States.
Frontiers in neuroscience
|August 16, 2023
概括
EfficientLIF-Net通过共享漏洞集成和火 (LIF) 神经元来减少尖端神经网络 (SNN) 的内存使用. 这种方法保持了准确性,同时显著提高了SNN的内存效率.
科学领域:
- 人工智能的人工智能
- 计算机科学 计算机科学
- 神经科学是一个神经科学.
背景情况:
- 尖端神经网络 (SNN) 通过二进制和异步操作提供节能计算.
- 泄漏集成和火 (LIF) 神经元对于SNN至关重要,需要大量的内存来存储膜电压以进行时间动态.
- 对LIF神经元的记忆需求随着输入尺寸的增加而升级,这对SNN可扩展性构成了挑战.
研究的目的:
- 引入一种用于减少SNNs内存消耗的新技术,特别是解决LIF神经元的内存需求.
- 开发一个高效的SNN架构,在优化内存使用的同时保持高精度.
主要方法:
- 提出了EfficientLIF-Net,这是一种新的SNN架构,可以在不同层和通道上共享LIF神经元.
- 在各种基准数据集上实施和评估了EfficientLIF-Net,包括CIFAR10,CIFAR100,TinyImageNet,ImageNet-100和N-Caltech101.
- 评估了EfficientLIF-Net对人类活动识别 (HAR) 数据集的性能,强调其在时间信息处理中的实用性.
主要成果:
- 实现了与标准SNN相提并论的准确性.
- 证明了显著的记忆效率增长:LIF神经元的记忆效率高达~4.3倍前进和~21.9倍后退.
- 在各种图像分类和HAR任务中验证了EfficientLIF-Net的有效性.
结论:
- EfficientLIF-Net提供了一个简单而有效的解决方案,可以提高SNN中的内存效率,而不会影响准确性.
- 拟议的神经元共享策略可以大大节省记忆,使SNN在大规模应用中变得更加实用.
- EfficientLIF-Net对于需要高效时间信息处理的应用程序,如HAR,是有前途的.
相关概念视频
Integration of Synaptic Events
1.6K
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...
1.6K
Neural Circuits
1.3K
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...
1.3K
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....
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
Graded Potential
4.0K
Graded potentials are localized fluctuations in the cell membrane's electrical charge, commonly found in the dendrites of neurons. The magnitude of these potential changes depends on the strength of the initiating stimulus. In a membrane at its resting potential, a graded potential signifies a voltage shift either above -70 mV or below -70 mV.
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
4.0K


