arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.08428eess.SP
收藏

一种用于基于事件的神经前端的采用存内计算的低功耗尖峰检测器

A Low-Power Spike Detector Using In-Memory Computing for Event-based Neural Frontend

Ye Ke, Arindam Basu

AI总结:

针对下一代脑机接口神经前端功耗与数据速率挑战,提出基于HRAM和存内计算的低功耗尖峰检测器,无需重构信号即可检测,在65nm工艺下实现92-99%准确率且每通道仅13.8nW功耗。

摘要:

随着下一代脑机接口(BMI)系统的传感器规模扩大,神经前端的大量模数转换与模拟多路复用给无线及植入式BMI的功耗和数据速率带来了挑战。已有研究报道了神经信号的神经形态压缩,但要实现进一步压缩需要将尖峰检测器集成在芯片上。本研究提出了一种高效的基于HRAM的尖峰检测器,采用存内计算架构,用于基于事件的压缩型神经前端。所提方法无需重构信号,直接从事件脉冲中检测尖峰,并使用10T混合存内计算位单元执行累加和阈值操作。实验表明,该方法在65nm CMOS工艺下,对神经信号输入的尖峰检测准确率可达92-99%,而每通道功耗仅为13.8nW。

英文摘要:

With the sensor scaling of next-generation Brain-Machine Interface (BMI) systems, the massive A/D conversion and analog multiplexing at the neural frontend poses a challenge in terms of power and data rates for wireless and implantable BMIs. While previous works have reported the neuromorphic compression of neural signal, further compression requires integration of spike detectors on chip. In this work, we propose an efficient HRAM-based spike detector using In-memory computing for compressive event-based neural frontend. Our proposed method involves detecting spikes from event pulses without reconstructing the signal and uses a 10T hybrid in-memory computing bitcell for the accumulation and thresholding operations. We show that our method ensures a spike detection accuracy of 92-99% for neural signal inputs while consuming only 13.8 nW per channel in 65 nm CMOS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑