BibTex format
@article{Wong:2020,
author = {Wong, MZ and Guillard, B and Murai, R and Saeedi, S and Kelly, PHJ},
title = {AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors},
url = {http://arxiv.org/abs/2006.01765v2},
year = {2020}
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - We present a high-speed, energy-efficient Convolutional Neural Network (CNN)architecture utilising the capabilities of a unique class of devices known asanalog Focal Plane Sensor Processors (FPSP), in which the sensor and theprocessor are embedded together on the same silicon chip. Unlike traditionalvision systems, where the sensor array sends collected data to a separateprocessor for processing, FPSPs allow data to be processed on the imagingdevice itself. This unique architecture enables ultra-fast image processing andhigh energy efficiency, at the expense of limited processing resources andapproximate computations. In this work, we show how to convert standard CNNs toFPSP code, and demonstrate a method of training networks to increase theirrobustness to analog computation errors. Our proposed architecture, coinedAnalogNet, reaches a testing accuracy of 96.9% on the MNIST handwritten digitsrecognition task, at a speed of 2260 FPS, for a cost of 0.7 mJ per frame.
AU - Wong,MZ
AU - Guillard,B
AU - Murai,R
AU - Saeedi,S
AU - Kelly,PHJ
PY - 2020///
TI - AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors
UR - http://arxiv.org/abs/2006.01765v2
ER -