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
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;
Conference_Titel :
Nanoscale Architectures (NANOARCH), 2015 IEEE/ACM International Symposium on
Conference_Location :
Boston, MA
DOI :
10.1109/NANOARCH.2015.7180611
