相关实验视频

Updated: Jun 27, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

高性能深尖神经网络通过最多两尖指数编码

Yunhua Chen¹, Ren Feng¹, Zhimin Xiong¹

¹School of Computer Science and Technology, Guangdong University of Technology, China.

Neural networks : the official journal of the International Neural Network Society

|May 7, 2024

概括

我们介绍了一种用于将人工神经网络 (ANN) 转换为尖端神经网络 (SNN) 的新方法,使用At-most-two-spike指数编码 (AEC). 这种方法提高了准确性,并显著提高了神经形态计算中的能源效率和推理延迟.

科学领域:

神经形态计算是一种神经形态计算.
人工智能的人工智能
计算神经科学是一种神经科学.

背景情况:

尖端神经网络 (SNN) 对于高效的神经形态计算至关重要.
将先进的人工神经网络 (ANN) 转换为SNN是高性能SNN开发的关键策略.
现有的转换方法在平衡精度,延迟和功耗方面面临挑战.

研究的目的:

通过基于时间的编码方案,提出一种新的ANN到SNN转换方法.
引入At-most-two-spike指数编码 (AEC) 方案和相应的AEC尖端神经元模型.
为了提高转换后的SNN的准确性,能源效率和推断延迟.

主要方法:

开发了At-most-two-spike指数编码 (AEC) 方案,使用了一种新的尖端神经元模型.
利用两个指数式衰变函数用于动态编码值来表示像素强度.
使用损失函数微调AEC神经元超参数,并为尖端数量引入规范化术语.

主要成果:

与现有的转换技术相比,AEC方法在深度SNNs中实现了更高的准确性.
在SNN推断中,显著提高了能源效率.
在使用AEC方案转换的SNN中展示了减少的推断延迟.

结论:

拟议的AEC转换方法为开发高性能SNNs提供了一种优越的方法.
AEC有效地平衡精度,延迟和功耗,使其适合神经形态应用.
这项工作为有效的SNN实施领域提供了宝贵的贡献.

关键词:

在 ANN-SNN 转换过程中,在最多两尖指数编码指数编码.深度尖的神经网络深度尖的神经网络基于时间的编码.

更多相关视频

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

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

相关概念视频

The Role of Ion Channels in Neuronal Computation

The Role of Ion Channels in Neuronal Computation

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....

Long-term Potentiation

Long-term Potentiation

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.