基于memristor的适应激活功能的异质霍普菲尔德神经网络的动态
Chunhua Wang1, Junhui Liang2, Quanli Deng2
1College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China; Greater Bay Area Institute for Innovation, Hunan University, Guangzhou, 511300, China.
概括
这项研究介绍了一种具有多种激活功能的新型异质记忆型霍普菲尔德神经网络 (HNN). 这项研究揭示了复杂的动态,并验证了硬件实现,推进了记忆神经网络研究.
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.
- 非线性动力学是一种非线性动力学.
背景情况:
- 记忆式霍普菲尔德神经网络 (HNN) 对非线性动态至关重要.
- 虽然研究了memristor效应,但激活函数对HNN动态的影响较少被探索.
研究的目的:
- 为了研究具有多种激活功能的异质记忆性HNN的动态.
- 探索一种基于memristor的自适应激活函数的作用.
- 对拟议的HNN模型进行理论和实验验证.
主要方法:
- 使用相位肖像,分叉图和莱普诺夫指数光谱进行动态分析.
- 开发了一种异质的记忆式HNN,包含固定和自适应激活功能.
- 执行了适应激活函数模型的硬件实现和实验验证.
主要成果:
- 观察到复杂的动态行为,包括多滚动混乱,短暂的混乱和状态跳跃.
- 证明了多种类型的共存吸引物的存在.
- 证实了数值模拟和实验结果之间的良好一致性.
结论:
- 不同质的记忆性HNN表现出丰富而复杂的动态.
- 基于memristor的自适应激活功能增强了HNN的能力.
- 硬件实现验证了理论发现,为实际应用铺平了道路.
相关概念视频
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
The Role of Ion Channels in Neuronal Computation
3.2K
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....
3.2K
MOS Capacitor
765
A Metal-Oxide-Semiconductor (MOS) capacitor is a fundamental structure used extensively in semiconductor device technology, particularly in the fabrication of integrated circuits and MOSFETs (metal-oxide-semiconductor field-effect transistors). The MOS capacitor consists of three layers: a metal gate, a dielectric oxide, and a semiconductor substrate.
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...
765
Long-term Potentiation
55.1K
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.
55.1K


