• DocumentCode
    3455569
  • Title

    On the impact of OxRAM-based synapses variability on convolutional neural networks performance

  • Author

    Garbin, D. ; Vianello, E. ; Bichler, O. ; Azzaz, M. ; Rafhay, Q. ; Candelier, P. ; Gamrat, C. ; Ghibaudo, G. ; DeSalvo, B. ; Perniola, L.

  • Author_Institution
    LETI, CEA, Grenoble, France
  • fYear
    2015
  • fDate
    8-10 July 2015
  • Firstpage
    193
  • Lastpage
    198
  • Abstract
    In this work, both temporal (cycle-to-cycle) and spatial (device-to-device) variability of hafnium oxide based OxRAM cells are investigated at array level. The impact of the resistance variability on OxRAM-based convolutional neural network is then evaluated. Two different types of neurons, analog and digital, are considered. Results show that the studied architecture is strongly immune to both temporal and spatial variability.
  • Keywords
    hafnium compounds; neural nets; random-access storage; HfO; OxRAM-based synapses; convolutional neural networks; cycle-to-cycle variability; device-to-device variability; spatial variability; temporal variability; Decision support systems; Driver circuits; Nanoscale devices; Neurons; Convolutional Neural Network; OxRAM; resistive memory; synapse; variability;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Nanoscale Architectures (NANOARCH), 2015 IEEE/ACM International Symposium on
  • Conference_Location
    Boston, MA
  • Type

    conf

  • DOI
    10.1109/NANOARCH.2015.7180611
  • Filename
    7180611