Spatial pattern formation via reaction-diffusion dynamics in 32×32×4 CNN chip
Spatial pattern formation via reaction-diffusion dynamics in 32×32×4 CNN chip
复制标题
32×32×4 CNN 芯片中通过反应扩散动力学形成空间模式
DOI：
10.1109/tcsi.2004.827628
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Tao Luo
中科院分区：
文献类型：
--
作者：
Bertram E. Shi;Tao Luo
已经提出反应扩散动力学来解释各种系统中的图案形成行为，例如，化学的和生物的。本文描述了一种细胞神经网络芯片，表现出空间组织的活动模式，这是由反应扩散形成的。该芯片包含四个32 - 32单元阵列的晶体管，这些晶体管是本地耦合和弱反相操作。典型的图案由具有优选宽度但没有优选取向的高漏极电流和低漏极电流的交替区域组成。该芯片的实验、理论和模拟结果完全一致，表明传统的超大规模集成技术可以成为研究反应扩散时空动力学和应用的理想衬底。该芯片，这是在0.5米的过程中制造的，解决了稳定状态的模式在几百微秒内和耗散10.55毫瓦。索引项-模拟超大规模集成电路（VLSI），细胞神经网络（CNN），CMOS，非线性电路，非线性动力学，模式形成，反应扩散，图灵模式，VLSI。
Reaction-diffusion dynamics have been proposed to explain pattern-formation behavior in a variety of systems, e.g., chemical and biological. This paper describes a cellular neural network chip that exhibits spatially organized patterns of activity, which are formed by reaction diffusion. The chip contains four 32 32 cell arrays of transistors which are locally coupled and operate in weak inversion. Typical patterns consist of alternating regions of high- and low-drain currents with a preferred width, but no preferred orientation. Experimental, theoretical, and simulation results for this chip are in complete concordance, demonstrating that conventional very large-scale integration tech- nology can be an ideal substrate for studying the spatio-temporal dynamics and applications of reaction-diffusion. The chip, which was fabricated in a 0.5- m process, settles to steady-state patterns within several hundred microseconds and dissipates 10.55 mW. Index Terms—Analog very large-scale integration (VLSI), cel- lular neural network (CNN), CMOS, nonlinear circuits, nonlinear dynamics, pattern formation, reaction diffusion, Turing pattern, VLSI.