配对竞争神经元改善STDP监督局部学习在尖端神经网络
Gaspard Goupy1, Pierre Tirilly1, Ioan Marius Bilasco1
1Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL, Lille, France.
Frontiers in neuroscience
|August 9, 2024
概括
我们介绍了稳定监督STDP (S2-STDP),这是一个新的学习规则,用于尖端神经网络 (SNNs). 这种方法通过整合错误调制更新和配对竞争神经元架构来提高神经形态硬件的分类准确性.
科学领域:
- 神经形态工程的神经形态工程
- 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) 在神经形态硬件上提供节能计算.
- 无监督的尖峰时间依赖可塑性 (STDP) 能够实现无梯度的学习,但不足以进行分类.
- 需要监督学习方法来适应SNN进行分类任务.
研究的目的:
- 开发SNN分类层的监督学习规则.
- 通过使用新的培训架构来提高SNN分类性能.
- 在神经形态平台上实现高效准确的基于SNN的图像识别.
主要方法:
- 拟议的稳定监督STDP (S2-STDP) 具有调节错误的重量更新,调整神经元尖峰.
- 介绍了用于神经元专业化和类内竞争的配对竞争神经元 (PCN) 架构.
- 在MNIST,时尚-MNIST和CIFAR-10图像识别数据集上评估了S2-STDP和PCN.
主要成果:
- 在分类准确性方面,S2-STDP的表现优于现有的监督STDP学习规则.
- 在PCN架构显著提高S2-STDP在各种数据集的性能.
- 在没有引入额外的超参数的情况下,PCN提高了S2-STDP的有效性.
结论:
- S2-STDP为SNN分类层提供了一种有效的监督学习方法.
- PCN架构是提高SNN分类能力的宝贵补充.
- 这些进步为神经形态硬件上更强大,更节能的SNN铺平了道路.
相关概念视频
01:25Long-term Potentiation
2.8K
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.
Hebbian LTP
LTP can occur when...
Hebbian LTP
LTP can occur when...
2.8K
01:25Neural Circuits
1.1K
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...
1.1K
01:32Postsynaptic Potential (PSP)
2.5K
Postsynaptic potential (PSP) refers to a change in the electrical potential of a neuron when neurotransmitters released by presynaptic neurons bind to postsynaptic receptors. This potential can either be excitatory, leading to depolarization and ultimately action potential generation, or inhibitory, leading to hyperpolarization and suppression of the postsynaptic neuron.
There are two types of receptors: ionotropic and metabotropic.
The ionotropic receptor is the membrane protein that has an...
There are two types of receptors: ionotropic and metabotropic.
The ionotropic receptor is the membrane protein that has an...
2.5K