记忆性泄漏的整合和发射神经元和可学习的直通估计器在尖端神经网络中
Tao Chen1, Chunyan She1, Lidan Wang1,2,3
1College of Artificial Intelligence, Southwest University, Chongqing, 400715 China.
Cognitive neurodynamics
|November 18, 2024
概括
尖端神经网络 (SNN) 通过使用一种新型记忆漏洞整合和火 (MLIF) 模型和可学习值估计器 (LSTE) 增强. 这提高了SNN的学习和表达,在神经形态数据集上实现了高精度.
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
- 神经形态工程的神经形态工程
背景情况:
- 尖端神经网络 (SNN) 提供了比人工神经网络 (ANN) 的生物可信性,这是由于事件驱动的,基于尖端的通信.
- 目前的SNN经常使用统一的漏洞整合和火 (LIF) 模型,限制神经动态的多样性和表现力.
- 生物神经系统中的异质性并没有被统一的参数模型所捕捉到.
研究的目的:
- 为SNN引入一个异质记忆性LIF (MLIF) 神经元模型.
- 开发一种可学习的直通估计器 (LSTE),以改善SNN中的梯度传播.
- 提高SNN的学习能力,表达能力和信息能力.
主要方法:
- 用一个离散的memristor替换了LIF模型中的电阻,以创建MLIF模型,实现动态膜时间参数.
- 通过LSTE引入一个可学习的值,基于直通估计器 (STE) 替代函数.
- 对静态和神经形态基准数据集进行了广泛的实验,包括DVS-CIFAR10.
主要成果:
- MLIF模型允许SNN根据膜潜力动态调整膜时间参数.
- LSTE通过具有可学习值的尖端神经元促进梯度反向传播.
- 在DVS-CIFAR10数据集上实现了84.40%的top-1精度,显示出显著的性能提升.
结论:
- 拟议的MLIF和LSTE显著提高了SNN的学习能力和表达力.
- 动态参数适应和可学习值对于提高SNN性能至关重要.
- 这些进步为更复杂和生物学上更现实的神经形态计算系统铺平了道路.
相关概念视频
The Role of Ion Channels in Neuronal Computation
3.1K
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....
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....
3.1K
Integration of Synaptic Events
1.4K
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...
1.4K
Neural 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
Graded Potential
3.7K
Graded potentials are localized fluctuations in the cell membrane's electrical charge, commonly found in the dendrites of neurons. The magnitude of these potential changes depends on the strength of the initiating stimulus. In a membrane at its resting potential, a graded potential signifies a voltage shift either above -70 mV or below -70 mV.
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
3.7K
Electrochemical Gradient and Channel Proteins: An Overview
2.0K
An electrochemical gradient is a fundamental concept in biology and chemistry. It regulates the movement of ions across cell membranes. This movement is influenced by two factors:
The electrical gradient: The electrical gradient across cell membranes refers to the difference in electric charge between the inside and outside of a cell. This difference drives the movement of ions towards or away from the cells. For instance, if the inside of the cell is more negatively charged relative to...
The electrical gradient: The electrical gradient across cell membranes refers to the difference in electric charge between the inside and outside of a cell. This difference drives the movement of ions towards or away from the cells. For instance, if the inside of the cell is more negatively charged relative to...
2.0K
Long-term Potentiation
2.7K
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...
2.7K


