相关实验视频

Updated: Jan 15, 2026

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

一热多级漏洞集成和火点神经网络,用于增强精度延迟权衡

Pierre Abillama¹, Changwoo Lee¹, Andrea Bejarano-Carbo¹

¹Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48109, USA.

IEEE access : practical innovations, open solutions

|October 16, 2025

概括

尖端神经网络 (SNN) 提供能源效率,但面临着延迟挑战. 一个新的单热多级泄漏的整合和发射 (M-LIF) 神经元模型改善了精度-能量权衡,优于传统的SNN.

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.
节能计算节能计算节能计算节能计算

背景情况:

尖端神经网络 (SNN) 是人工神经网络 (ANN) 的节能替代品.
将SNN延迟减少到单个时间步骤可以提高能源效率,但往往会降低精度.
在SNN中平衡精度和能源消耗仍然是一个重大挑战.

研究的目的:

引入一种新的神经元模型,增强SNN中的精度-能量权衡.
探索一个新的维度,以优化SNN性能,使用一热多层泄漏的整合和发射 (M-LIF) 神经元.
证明拟议模型对静态和动态视觉数据集的有效性.

主要方法:

开发了一种新的一热多级泄漏的整合与火 (M-LIF) 神经元模型.
代表隐藏层输入/输出使用一热二进制加权尖车道.
对静态图像分类 (ImageNet) 和动态视觉数据集的模型进行了评估.

主要成果:

一次热的M-LIF SNNs在ImageNet上比传统的LIF SNNs高出2%的精度,能源消耗比ANNs低20倍.
对于动态视觉任务,M-LIF SNNs比传统LIF SNNs减少了3倍的延迟时间.
在动态视觉任务中,精度降低仅限于不到1%.

结论:

一次热的M-LIF神经元模型有效地改善了SNN中的精度-能量权衡.
这种新的方法使SNN能够实现卓越的性能和能源效率.
M-LIF模型提供了一种可行的解决方案,可以在没有显著的准确性损失的情况下减少延迟.

关键词:

尖的神经网络的神经网络.能源效率是指能效的能源效率.低延迟的低延迟时间多层次的多层次的一个热门的热门.

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

相关概念视频

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

Integration of Synaptic Events

Integration of Synaptic Events

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...