An Energy-Efficient Mixed-Signal Neuron for Inherently Error-Resilient Neuromorphic Systems

2017/10/24 by Chatterjee, Baibhab, Panda, Priyadarshini, Maity, Shovan +2
#Artificial Intelligence (cs.AI) #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #Hardware Architecture (cs.AR)

paper · doi:10.48550/arxiv.1710.09012

Abstract

This work presents the design and analysis of a mixed-signal neuron (MS-N) for convolutional neural networks (CNN) and compares its performance with a digital neuron (Dig-N) in terms of operating frequency, power and noise. The circuit-level implementation of the MS-N in 65 nm CMOS technology exhibits 2-3 orders of magnitude better energy-efficiency over Dig-N for neuromorphic computing applications - especially at low frequencies due to the high leakage currents from many transistors in Dig-N. The inherent error-resiliency of CNN is exploited to handle the thermal and flicker noise of MS-N. A system-level analysis using a cohesive circuit-algorithmic framework on MNIST and CIFAR-10 datasets demonstrate an increase of 3% in worst-case classification error for MNIST when the integrated noise power in the bandwidth is ~ 1 μV2.

Related

• Exploiting Inherent Error-Resiliency of Neuromorphic Computing to achieve Extreme Energy-Efficiency through Mixed-Signal Neurons
• Improving Noise Tolerance of Mixed-Signal Neural Networks
• A 1.6-fJ/Spike Subthreshold Analog Spiking Neuron in 28 nm CMOS
• Sub-1-us, Sub-20-nJ Pattern Classification in a Mixed-Signal Circuit Based on Embedded 180-nm Floating-Gate Memory Cell Arrays
• INsight: A Neuromorphic Computing System for Evaluation of Large Neural Networks