相关实验视频

Updated: Jun 22, 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

自我架构的知识蒸用于尖端的神经网络

Haonan Qiu¹, Munan Ning¹, Zeyin Song¹

¹Peking University, School of Electronic and Computer Engineering, Shenzhen Graduate School, China.

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

|June 28, 2024

概括

自主架构知识蒸 (SAKD) 通过平衡性能和低延迟来增强尖端神经网络 (SNN). 这种方法在基准上以较少的时间步骤实现了最先进的结果,提高了SNN的效率.

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.
机器学习机器学习

背景情况:

尖端神经网络 (SNN) 为神经形态硬件提供了生物可信性和低能计算潜力.
当前的SNN培训方法面临着性能 (ANN-SNN转换) 和延迟 (直接培训) 之间的权衡.

研究的目的:

解决神经网络尖端的性能延迟权衡问题.
引入一种新的方法,即自我架构知识蒸 (SAKD),用于训练SNN.

主要方法:

建议使用双层教师-学生战略进行自我架构知识蒸 (SAKD).
第1级:直接将预训练的人工神经网络 (ANN) 重量转移到SNNs.
第二级:鼓励SNN模仿ANN的行为,包括中间特征和最终输出.

主要成果:

在最小时间步骤的分类基准上实现了新的最先进的 (SOTA) 性能.
在ImageNet-1K上,Spiking-ResNet34在4个时间步骤中获得了70.04%的Top-1精度.
在ImageNet-1K上,SEW-ResNet152实现了77.30%的Top-1精度,为SNNs设置了一个新的SOTA.
在下游任务,如对象检测和语义细分等方面表现出强大的概括性.

结论:

在SNN中,SAKD有效地平衡了高性能和低延迟.
拟议的框架显示了SNN在节能AI方面取得的重大进展.
SAKD为未来的SNN研究和应用提供了一个有希望的方向.

关键词:

一个ANN到一个SNN.图像的分类图像的分类.知识的蒸知识的蒸.语义细分语义细分是指语义细分.尖的神经网络的神经网络.

更多相关视频

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

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

相关概念视频

Neural Circuits

Neural Circuits

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...

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...

Neuroplasticity

Neuroplasticity

Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.