相关实验视频
Updated: Jun 14, 2025

07:38
Author Spotlight: Modular Neuronal Networks for Analyzing Brain Functions
Published on: June 7, 2024
1.5K
NEXUS:一个28nm 3.3pJ/SOP 16核尖端神经网络,具有钻石拓,用于实时数据处理
IEEE transactions on biomedical circuits and systems
|August 30, 2024
概括
这项研究介绍了NEXUS,这是一款16核尖端神经网络 (SNN) 芯片,可以克服大脑规模AI的功率和密度限制. 它的新型网络上芯片 (NoC) 架构确保了高效,无数据损失的通信,用于先进的神经形态计算.
科学领域:
- 神经形态工程的神经形态工程
- 集成电路设计 集成电路设计
- 人工智能的人工智能
背景情况:
- 大脑规模的尖端神经网络 (SNN) 面临着电力和集成密度的挑战.
- 现有的多核SNN使用Network-on-Chip (NoC) 以提高效率,但在高流量的情况下会遭受信息丢失.
- 这就需要新的架构来实现可靠和高效的神经形态硬件.
研究的目的:
- 为了介绍NEXUS,一个16核SNN芯片,具有新的钻石形NoC拓.
- 展示一个可扩展的NoC架构,可以防止数据丢失并最大限度地降低延迟.
- 为了展示一个紧的路由器设计和一个神经突触核心,使速度增强.
主要方法:
- 使用28纳米CMOS技术制造一个16核SNN芯片,集成4096个漏洞集成和火 (LIF) 神经元和1M的突触重量.
- 实施钻石形NoC拓,采用一种新的拥堵管理方法,消除FIFO.
- 将神经网络模型 (MNIST分类,音频识别) 映射到制造的芯片上.
主要成果:
- NEXUS芯片实现了高性能,峰值吞吐量为4.7GSOP/s,能耗低 (3.3 pJ/SOP).
- 该NoC确保没有数据丢失,最大延迟为5.1微秒,并具有紧的路由器足迹 (0.001毫米2).
- 在MNIST分类 (8.4K-分类/s) 中,准确度为92.3%,在音频识别中,准确度为87.4%.
结论:
- NEXUS为大脑规模的SNN提供了可扩展和节能的解决方案,解决了当前神经形态硬件的关键局限性.
- 拟议的NoC架构和拥堵管理对于高流量SNNs的可靠数据传输至关重要.
- 芯片在分类和识别任务中的性能验证了其对现实世界AI应用的潜力.
更多相关视频
10:45Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling
Published on: May 31, 2017
13.1K
05:19Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
Published on: November 12, 2019
7.0K
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
Neurons: The Axon
3.3K
Axons are long, cytoplasmic processes of nerve cells capable of propagating electrical impulses known as action potentials. The cytoplasm or axoplasm of an axon contains neurofibrils, neurotubules, small vesicles, lysosomes, mitochondria, and various enzymes, all encased within the axolemma, the plasma membrane of the axon.
The axon attaches to the cell body at a cone-shaped elevation called the axon hillock. The initial part of the axon, closest to the hillock, is known as the initial segment....
The axon attaches to the cell body at a cone-shaped elevation called the axon hillock. The initial part of the axon, closest to the hillock, is known as the initial segment....
3.3K
Electrical Synapses
8.2K
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...
8.2K
Ampere-Maxwell's Law: Problem-Solving
567
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
567
Fast Decoupled and DC Powerflow
178
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
178
Overview of Synapses
2.2K
A synapse is a specialized structure where two neurons connect, allowing them to pass an electrical or chemical signal to another neuron. It is the point of communication between neurons. The term "synapse" is derived from the Greek word "synapsis," which means "conjunction." The entire process of neural communication revolves around the synapse. When activated, a neuron releases chemicals known as neurotransmitters into the synapse. These neurotransmitters cross the synapse and bind to...
2.2K