A study of brain-like integrated systems using nonlinear dynamics with pulse phase

利用脉冲相位非线性动力学研究类脑集成系统

• 批准号: 13835005
• 负责人: MORIE Takashi
• 金额: $ 2.3万
• 依托单位: Kyushu Institute of Technology (2002)Hiroshima University (2001)
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2001
• 资助国家: 日本
• 起止时间: 2001 至 2002
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-13835005/
• 关键词: pulse modulation method; spiking neuron; integrate-and-fire-neuron; Hopfield networks; associative memory; nanodot MOSFET; nanotechnology; パルス幅変調方式

1. Development of an image processing LSI using nonlinear dynamics with pulse timingAn oscillator network LSI that performs image region segmentation and extraction using oscillation phase synchronization was designed using analog-digital merged/mixed architecture. In this LSI, the circuit block for nonlinear dynamics consists of pulse modulation circuits, and the weight memory and control part consists of digital circuits.2. Development of an algorithm for brain-like information processing circuits using pulse timingBy applying a spiking neuron model (integrate-and-fire type) to feedback networks, we can operate the networks faster. The basic concept is that signals inputted earlier are considered more important. To discriminate between feedback signals and late-inputted signals, a global inhibitor neuron with ramped inhibition and a reset mechanism at firing in a neuron are introduced. From the circuit simulation results of associative memory operation in Hopfield networks with 20 neurons, it was confirmed that the proposed circuit converges 20 times faster than the conventional pulse-width modulation circuit.3. Design of a spiking neuron circuit with multi-nanodot MOSFETsFor a circuit technique in the post-CMOS era, a spiking neuron circuit with multi-nanodot MOSFETs is proposed. The circuit can generate a post-synaptic potential much more efficiently and with ultra-low power dissipation. The nanodot structure will be constructed by using self-assembly processes using nanotechnology.

1.利用非线性动力学和脉冲定时的图像处理LSI的开发利用模拟-数字合并/混合结构设计了一个振荡器网络LSI，该LSI利用振荡相位同步执行图像区域分割和提取。在该LSI中，非线性动力学的电路块由脉冲调制电路组成，权重存储和控制部分由数字电路组成.利用脉冲定时的类脑信息处理电路算法的开发通过将脉冲发放神经元模型（积分-激发型）应用于反馈网络，我们可以更快地操作网络。基本概念是，较早输入的信号被认为更重要。为了区分反馈信号和迟输入信号，引入了具有斜坡抑制的全局抑制神经元和神经元激发时的重置机制。在20个神经元的Hopfield网络中进行联想记忆操作的电路仿真结果表明，该电路的收敛速度比传统的脉宽调制电路快20倍.基于多纳米点MOSFET的尖峰神经元电路设计针对后CMOS时代的电路技术，提出了一种基于多纳米点MOSFET的尖峰神经元电路。该电路可以更有效地产生突触后电位，并且具有超低功耗。纳米点结构将通过使用纳米技术的自组装过程来构建。

项目成果

H.Ando, T.Morie, M.Nagata, A.Iwata: "An Image Region Extraction LSI Based on a Merged/Mixes-Signal Nonlinear Oscillator Network Circui"28th European Solid-State Circuits Conference (ESSCIRC2002). 703-706 (2002)

H.Ando、T.Morie、M.Nagata、A.Iwata：“基于合并/混合信号非线性振荡器网络电路的图像区域提取 LSI”第 28 届欧洲固态电路会议 (ESSCIRC2002)。

A.Iwata, T.Morie, M.Nagata: "Bio-Inspired VLSIs Based on Analog/Digital Merged Technologies"Extended Abstracts of the 2001 Int.Conf.Solid State Devices and Materials. 88-89 (2001)

A.Iwata、T.Morie、M.Nagata：“基于模拟/数字合并技术的仿生 VLSI”2001 年 Int.Conf.Solid State Devices and Materials 的扩展摘要。

H.Ando, T.Morie, M.Nagata, A.Iwata: "An Image Region Extraction LSI Based on a Merged/Mixed-Signal Nonlinear Oscillator Network Circuit"28th European Solid-State Circuits Conference. 703-706 (2002)

H.Ando、T.Morie、M.Nagata、A.Iwata：“基于合并/混合信号非线性振荡器网络电路的图像区域提取 LSI”第 28 届欧洲固态电路会议。

T.Morie, T.Matsuura, M.Nagata, A.Iwata: "A Multi-Nanodot Floating-Gate MOSFET Circuit for Spiking Neuron Models"2002 IEEE Silicon Nanoelectronics Workshop. 53-54 (2002)

T.Morie、T.Matsuura、M.Nagata、A.Iwata：“用于尖峰神经元模型的多纳米点浮栅 MOSFET 电路”2002 年 IEEE 硅纳米电子研讨会。

Morie., T.Matsuura., M.Nagata., and A.Iwata.: "A Multi-Nanodot Floating-Gate MOSFET Circuit for Spiking Neuron Models"2002 IEEE Silicon Nanoelectronics Workshop. 53-54 (2002)

Morie.、T.Matsuura.、M.Nagata. 和 A.Iwata.：“用于尖峰神经元模型的多纳米点浮栅 MOSFET 电路”2002 年 IEEE 硅纳米电子研讨会。