A design methodology for fault-tolerant computing using astrocyte neural networks

Abstract

We propose a design methodology to facilitate fault tolerance of deep learning models. First, we implement a many-core fault-tolerant neuromorphic hardware design, where neuron and synapse circuitries in each neuromorphic core are enclosed with astrocyte circuitries, the star-shaped glial cells of the brain that facilitate selfrepair by restoring the spike firing frequency of a failed neuron using a closed-loop retrograde feedback signal. Next, we introduce astrocytes in a deep learning model to achieve the required degree of tolerance to hardware faults. Finally, we use a system software to partition the astrocyte-enabled model into clusters and implement them on the proposed fault-tolerant neuromorphic design. We evaluate this design methodology using seven deep learning inference models and show that it is both area-and power-efficient. CCS CONCEPTS• Hardware → Neural systems; • Computer systems organization → Dependable and fault-tolerant systems and networks.

A Digital Realization of Neuroglial Interaction Model and Its Network Structure

“…Based on their research work, 5 multipliers are reported in the high-level utilization table. A hardware cost comparison has been performed between the proposed astrocyte model in this work and two recently published articles according to different calciumbased astrocytic models in [53]- [54]. A digital design for an astrocyte model is implemented on FPGA platform which uses four DSP blocks and four block RAMs [53].…”

“…A hardware cost comparison has been performed between the proposed astrocyte model in this work and two recently published articles according to different calciumbased astrocytic models in [53]- [54]. A digital design for an astrocyte model is implemented on FPGA platform which uses four DSP blocks and four block RAMs [53]. In [54], a set of piecewise linear approximation is presented for an astrocytic-based calcium signalling with the maximum speed of 81MHz.…”

Neuromorphic applications in medicine

“…Lastly, neuromorphic hardware is fault-tolerant, meaning it can function even if individual components fail [26][27][28]. In traditional computing systems, individual components, such as transistors, can fail causing large portions of the system to malfunction.…”