基于双极NbO挥发性值装置的双向热感应泄漏整合和发火 (LIF) 神经元模型,具有超低操作电流的超低操作电流
Jianhui Zhao1, Liang Tong1, Jiangzhen Niu1
1Key Laboratory of Brain-Like Neuromorphic Devices and Systems of Hebei Province, College of Electronic and Information Engineering, Institute of Life Science and Green Development, Hebei University, Baoding 071002, China. xiaobing_yan@126.com.
Nanoscale
|October 24, 2023
概括
研究人员使用低电流memristor开发了一种新型的人工神经元. 这种由大脑启发的计算组件模仿神经功能,处理温度,并提供节能的人工智能.
科学领域:
- 材料科学 材料科学 材料科学
- 神经科学是一个神经科学.
- 计算机科学 计算机科学
背景情况:
- 类似大脑的人工智能 (AI) 对未来的计算至关重要,需要有效模拟大脑功能.
- 开发模仿生物过程的人工神经元和突触是先进AI系统的关键.
- 当前的人工智能硬件在能源消耗和集成密度方面面临挑战.
研究的目的:
- 为人工神经元构建双极挥发性值记忆器.
- 开发一个有漏洞的整合和发射 (LIF) 人工神经元,能够进行双向信号传输和温度传感.
- 提高计算效率,减少人工神经网络中的能源消耗.
主要方法:
- 一个NbO2双极挥发性值记忆器的制造.
- 实现一个漏洞整合和发射 (LIF) 人工神经元模型.
- 记忆器的电特性和神经元的功能反应的表征.
主要成果:
- 记忆器在超低电流 (1μA) 运行,开关比率高 (∼104).
- 构建的双极LIF人造神经元表现出值驱动的发射,全或零的尖峰和耐火期.
- 神经元表现出双向的促进/抑郁信号和强度调节的频率响应.
- 人工神经元可以处理温度信息,充当热感应神经元.
结论:
- 开发的基于memristor的人工神经元推进了类似大脑的计算.
- 这项技术可以实现更高效,更紧,更低能耗的人工神经网络.
- 热传感能力为智能机器人系统提供了新的可能性.
相关概念视频
Thermosensation
30.5K
Peripheral thermosensation is the perception of external temperature. A change in temperature (on the surface of the skin and other tissues) is detected by a family of temperature-sensitive ion channels called Transient Receptor Potential, or TRP, receptors. These receptors are located on free nerve endings. Those detecting cold temperatures are closer to the surface of the skin than the nerve endings detecting warmth. These thermoTRP channels, while temperature selective, have relatively...
30.5K
Integration of Synaptic Events
1.5K
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 to...
1.5K
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
Bipolar Junction Transistor
783
Bipolar Junction Transistors (BJTs) are essential elements in electronic circuits, playing a crucial role in the functionality of amplifiers, memories, and microprocessors. These transistors can be designed as NPN or PNP based on their doping patterns. They consist of three layers: the emitter, base, and collector. The configuration of these layers and their respective doping levels—with N-type or P-type impurities—define the transistor's type and its operational...
783
Electrical Synapses
8.3K
Electrical synapses found in all nervous systems play important and unique roles. In these synapses, the presynaptic and postsynaptic membranes are very close together (3.5 nm) and are actually physically connected by channel proteins forming gap junctions.
Gap junctions allow the current to pass directly from one cell to the next. In contrast, in the chemical synapse, the neurotransmitters carry the information through the synaptic cleft from one neuron to the next. They consist of two...
Gap junctions allow the current to pass directly from one cell to the next. In contrast, in the chemical synapse, the neurotransmitters carry the information through the synaptic cleft from one neuron to the next. They consist of two...
8.3K


