Variability-tolerant Convolutional Neural Network for Pattern Recognition applications based on OxRAM synapses

D. Garbin (1, 2) , O. Bichler (3) , E. Vianello (1) , Q. Rafhay (2) , C. Gamrat (3) , L. Perniola (1) , G. Ghibaudo (2) , B. Desalvo (1)

1 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
2 IMEP-LAHC - Institut de Microélectronique, Electromagnétisme et Photonique - Laboratoire d'Hyperfréquences et Caractérisation
3 DACLE-LIST - Département d'Architectures, Conception et Logiciels Embarqués-LIST

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

Domains: Engineering Sciences [physics]; Computer Science [cs]

D. Garbin, O. Bichler, E. Vianello, Q. Rafhay, C. Gamrat, et al.. Variability-tolerant Convolutional Neural Network for Pattern Recognition applications based on OxRAM synapses. 2014 IEEE International Electron Devices Meeting, Dec 2014, San Francisco, United States. pp.28.4.1-28.4.4, ⟨10.1109/IEDM.2014.7047126⟩. ⟨cea-01839848⟩