在尖端神经网络中进行无监督的培训后学习.
Reyhaneh Naderi1, Arash Rezaei1, Mahmood Amiri2
1Medical Technology Research Center, Institute of Health Technology, Kermanshah University of Medical Sciences, Kermanshah, Iran.
Scientific reports
|May 21, 2025
概括
尖端神经网络 (SNN) 现在可以在初始训练后学习,而不会改变突触重量. 这通过将长期尖峰时间依赖的可塑性 (STDP) 与短期可塑性 (STP) 结合起来来实现,以提高计算能力.
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:
- 人类大脑利用多种学习策略,但尖端神经网络 (SNN) 通常只采用一种,比如尖端时间依赖可塑性 (STDP).
- 传统的神经网络是训练并固定,缺乏适应新信息的训练后适应能力.
研究的目的:
- 调查短期可塑性 (STP) 是否可以使SNN在不改变突触重量的情况下进行训练后的学习.
- 通过整合多个学习规则来增强SNNs的生物可信性和计算能力.
主要方法:
- 综合三重组STDP用于长期学习,STP用于短期,培训后的学习.
- 为图像分类开发了两个无监督学习管道,将动态突触模型纳入训练有素的SNN.
主要成果:
- 与传统的培训方法相比,拟议的方法实现了更高的分类准确性.
- 国家统一网络显示了更快的融合率,表明学习效率有所提高.
- 通过将STP集成到SNN中,成功地证明了在SNN中培训后学习的可行性.
结论:
- 短期可塑性 (STP) 可以有效地集成到尖端神经网络 (SNN) 中,以便在初始训练后进行学习.
- 这种方法提高了生物可信性和计算性能,为神经网络开发提供了一个新的范式.
- 未来的研究应该探索这种培训后学习概念对各种挑战和数据集的应用.
相关概念视频
01:35Long-term Potentiation
54.6K
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.
54.6K
01:32Postsynaptic Potential (PSP)
2.2K
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...
2.2K