一个无监督的基于STDP的尖端神经网络,灵感来自生物学上可信的学习规则和连接
Yiting Dong1, Dongcheng Zhao2, Yang Li3
1School of Future Technology, University of Chinese Academy of Sciences, Beijing, China; Brain-Inspired Cognitive Intelligence Lab, Institute of Automation, Chinese Academy of Sciences (CAS), Beijing, China.
概括
这项研究使用受大脑可塑性启发的自适应机制来增强无监督尖端神经网络 (SNN). 这种新的方法显著提高了复杂数据集的训练速度和性能,优于传统方法.
科学领域:
- 计算神经科学是一种神经科学.
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 深度学习严重依赖于标记的数据,与人类学习不同.
- 尖端神经网络 (SNN) 与尖端时间依赖可塑性 (STDP) 是有前途的,但具有性能限制.
- 现有的SNN在无监督学习效率和复杂任务方面扎.
研究的目的:
- 以生物学习机制为灵感,为SNN开发一个改进的无监督学习模型.
- 通过适应性可塑性增强SNN的表现和学习能力.
- 加速和稳定无人监督的SNNs的复杂模式识别培训.
主要方法:
- 引入了适应性突触过器和适应性尖端值,用于神经元可塑性.
- 集成的自适应侧面抑制连接用于动态尖峰平衡.
- 开发了一个样本时间批次STDP (STB-STDP) 以实现高效的重量更新.
- 整合了这些适应机制,创建了一个新的无监督SNN培训框架.
主要成果:
- 在MNIST和FashionMNIST数据集上实现了基于STDP的无监督SNN的最新性能.
- 在复杂的CIFAR10数据集上表现出卓越的性能,标志着STDP-SNN无监督的首次应用到该数据集.
- 与监督的人工神经网络 (ANN) 相比,在小样本学习场景中表现出显著的优势.
结论:
- 拟议的适应机制和STB-STDP大大提高了无监督SNN培训的速度和性能.
- 该模型为SNNs的无监督学习提供了一个强大的新方法,特别是在复杂和有限数据的场景中.
- 这项工作弥合了生物学习和人工神经网络之间的差距,为更高效和更类似人类的人工智能铺平了道路.
相关概念视频
01:32Postsynaptic Potential (PSP)
2.7K
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...
2.7K
01:25Neural Circuits
1.3K
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...
1.3K
01:35Long-term Potentiation
55.4K
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.
55.4K
01:01Neuroplasticity
588
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.
588