Variability-tolerant Convolutional Neural Network for Pattern Recognition applications based on OxRAM synapses
Abstract
Software implementations of artificial Convolutional Neural Networks (CNNs), taking inspiration from biology, are at the state-of-the-art for Pattern Recognition (PR) applications and they are successfully used in commercial products [1]. However, they require power-hungry CPU/GPU to perform convolution operations based on computationally expensive sums of multiplications. This hinders their integration in portable devices. Some full CMOS-based hardware implementations of CNN have been suggested, but they still require the computation of multiplications [2]. In this work, we present for the first time to our knowledge a spike-based hardware implementation of CNN using HfO2 based OxRAM devices as binary synapses. OxRAM devices are chosen for their low switching energy [3] and promising endurance performance [4]. We perform an experimental and theoretical study of the impact of programming conditions at both device and system levels. A complex visual pattern recognition application is demonstrated with a spike-based hierarchical CNN, inspired from the mammalian visual cortex organization. A high accuracy (pattern recognition rate >94%) is obtained for all the tested programming conditions, even if the variability associated to weaker programming conditions is larger.
Keywords
Convolution
Visual pattern recognition
Mammals
Convolutional neural network
Commercial products
Hardware implementations
Complex networks
Application programs
Variability tolerant
Hardware
Neural networks
Pattern recognition
Theoretical study
Mammalian visual cortex
Electron devices
Software implementation