一个完全基于整数的尖端神经网络,具有动态值适应能力
Chenglong Zou1,2, Xiaoxin Cui3, Shuo Feng3
1Peking University Chongqing Research Institute of Big Data, Chongqing, China.
Frontiers in neuroscience
|January 1, 2025
概括
本研究介绍了一种高效的尖端神经网络 (SNN) 算法,可以在最小的时间步骤中实现高精度. 这种新的方法提高了边缘计算应用的能源效率.
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) 提供能源效率,但在实现高精度和快速推断方面面临挑战.
- 传统的ANN到SNN转换方法常常会出现突发的同步错误.
研究的目的:
- 提出一种新的SNN建模算法,以提高准确性和推断速度.
- 为了解决SNNs中的spiking同步错误.
- 提高SNN的硬件兼容性和能源效率.
主要方法:
- 开发了一种复杂的SNN算法,具有动态值适应机制.
- 将所有SNN变量 (膜潜力,值,突触重量) 量化为整数.
- 实施了尖端的LeNet和VGG-Net架构. 实现了尖端的LeNet和VGG-Net架构.
主要成果:
- 在MNIST上达到>99.45%的精度,在CIFAR-10上达到>93.15%的精度,分别只有4个和8个时间步骤.
- 整数量化显著减少了计算操作.
- 证明了与硬件实现的高度兼容性.
结论:
- 拟议的SNN算法有效地克服了传统方法的局限性.
- 基于整数的量化和动态值调整导致了高精度和效率.
- 这种方法对节能边缘计算应用具有重大潜力.
相关概念视频
Integration of Synaptic Events
1.3K
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...
1.3K
Graded Potential
3.4K
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...
3.4K
The Role of Ion Channels in Neuronal Computation
3.1K
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....
3.1K


