当前位置: X-MOL 学术IEEE Trans. Biomed. Circuits Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Recursive Threshold Logic - A Bioinspired Reconfigurable Dynamic Logic System with Crossbar Arrays
IEEE Transactions on Biomedical Circuits and Systems ( IF 3.8 ) Pub Date : 2020-12-01 , DOI: 10.1109/tbcas.2020.3027554
Alex James , Olga Krestinskaya , Akshay Maan

The neuron behavioral models are inspired by the principle of the firing of neurons, and weighted accumulation of charge for a given set of input stimuli. Biological neurons show dynamic behavior through its feedback and feedforward time-dependent responses. The principle of the firing of neurons inspires threshold logic design by applying threshold functions on the weight summation of inputs. In this article, we present a recursive threshold logic unit that uses the output feedback from standard threshold logic gates to emulate Boolean expressions in a time-sequenced manner. The Boolean expression is implemented with an analog resistive divider in memristive crossbars and a hard-threshold function designed with CMOS comparator for realizing the sums (OR) and products (AND) operators. The method benefits from reliable programming of the memristors in 1T1R crossbar configuration to suppress sneak path currents and thus enable larger crossbar sizes, which in turn allow a higher number of Boolean inputs. The reference threshold voltage for the decision comparators is tuned to implement AND and OR logic. The threshold value range is limited by the number of inputs to the crossbar. Simultaneously, the resistance of the memristors is kept constant at $R_{ON}$. The circuit's tolerance to the memristor variability and aging are analyzed, showing sufficient resilience. Also, the proposed recursive logic uses fewer cross-points, and has lower power dissipation than other memristive logic and CMOS implementation.

中文翻译:

递归阈值逻辑 - 具有交叉阵列的仿生可重构动态逻辑系统

神经元行为模型的灵感来自于神经元放电原理以及给定输入刺激集的电荷加权累积。生物神经元通过其反馈和前馈时间相关反应显示动态行为。通过对输入的权重总和应用阈值函数,神经元激发的原理启发了阈值逻辑设计。在本文中,我们提出了一个递归阈值逻辑单元,它使用来自标准阈值逻辑门的输出反馈以时序方式模拟布尔表达式。布尔表达式使用忆阻交叉开关中的模拟电阻分压器和使用 CMOS 比较器设计的硬阈值函数来实现,用于实现和 (OR) 和乘积 (AND) 运算符。该方法受益于 1T1R 交叉开关配置中忆阻器的可靠编程,以抑制潜路径电流,从而实现更大的交叉开关尺寸,从而允许更多数量的布尔输入。决策比较器的参考阈值电压经过调整以实现 AND 和 OR 逻辑。阈值范围受交叉开关的输入数量限制。同时,忆阻器的电阻保持恒定在 $R_{ON}$。分析了电路对忆阻器可变性和老化的耐受性,显示出足够的弹性。此外,所提出的递归逻辑使用更少的交叉点,并且比其他忆阻逻辑和 CMOS 实现具有更低的功耗。这反过来又允许更多的布尔输入。决策比较器的参考阈值电压经过调整以实现 AND 和 OR 逻辑。阈值范围受交叉开关的输入数量限制。同时,忆阻器的电阻保持恒定在 $R_{ON}$。分析了电路对忆阻器可变性和老化的耐受性,显示出足够的弹性。此外,所提出的递归逻辑使用更少的交叉点,并且比其他忆阻逻辑和 CMOS 实现具有更低的功耗。这反过来又允许更多的布尔输入。决策比较器的参考阈值电压经过调整以实现 AND 和 OR 逻辑。阈值范围受交叉开关的输入数量限制。同时,忆阻器的电阻保持恒定在 $R_{ON}$。分析了电路对忆阻器可变性和老化的耐受性,显示出足够的弹性。此外,所提出的递归逻辑使用更少的交叉点,并且比其他忆阻逻辑和 CMOS 实现具有更低的功耗。分析了电路对忆阻器可变性和老化的耐受性,显示出足够的弹性。此外,所提出的递归逻辑使用更少的交叉点,并且比其他忆阻逻辑和 CMOS 实现具有更低的功耗。分析了电路对忆阻器可变性和老化的耐受性,显示出足够的弹性。此外,所提出的递归逻辑使用更少的交叉点,并且比其他忆阻逻辑和 CMOS 实现具有更低的功耗。
更新日期:2020-12-01
down
wechat
bug