IEEE Trans Neural Netw Learn Syst. 2018 Apr;29(4):1287-1300. doi: 10.1109/TNNLS.2017.2673021. Epub 2017 Mar 6.
Recent research has shown that a glial cell of astrocyte underpins a self-repair mechanism in the human brain, where spiking neurons provide direct and indirect feedbacks to presynaptic terminals. These feedbacks modulate the synaptic transmission probability of release (PR). When synaptic faults occur, the neuron becomes silent or near silent due to the low PR of synapses; whereby the PRs of remaining healthy synapses are then increased by the indirect feedback from the astrocyte cell. In this paper, a novel hardware architecture of Self-rePAiring spiking Neural NEtwoRk (SPANNER) is proposed, which mimics this self-repairing capability in the human brain. This paper demonstrates that the hardware can self-detect and self-repair synaptic faults without the conventional components for the fault detection and fault repairing. Experimental results show that SPANNER can maintain the system performance with fault densities of up to 40%, and more importantly SPANNER has only a 20% performance degradation when the self-repairing architecture is significantly damaged at a fault density of 80%.
最近的研究表明，星形胶质细胞中的神经胶质细胞为人类大脑的自我修复机制提供了支持，其中尖峰神经元为突触前末梢提供直接和间接的反馈。这些反馈调节了释放（PR）的突触传递概率。当发生突触故障时，由于突触的 PR 较低，神经元变得沉默或几乎沉默；因此，通过星形胶质细胞的间接反馈，剩余健康突触的 PR 会增加。在本文中，提出了一种新型的自修复尖峰神经网络（SPANNER）硬件架构，该架构模拟了人类大脑中的这种自我修复能力。本文证明，该硬件可以在没有传统故障检测和修复组件的情况下进行自我检测和自我修复突触故障。实验结果表明，SPANNER 可以在故障密度高达 40%的情况下保持系统性能，更重要的是，当自修复架构在故障密度为 80%时受到严重损坏时，其性能仅下降 20%。
