Boybat, IremGiovinazzo, CeciliaShahrabi, ElmiraKrawczuk, IgorGiannopoulos, JasonPiveteau, ChristopheLe Gallo, ManuelRicciardi, CarloSebastian, AbuEleftheriou, EvangelosLeblebici, Yusuf2019-09-192019-09-192019-09-192019-01-0110.1109/ISCAS.2019.8702714https://infoscience.epfl.ch/handle/20.500.14299/161265WOS:000483076402180Metal-oxide-based resistive memory devices (ReRAM) are being actively researched as synaptic elements of neuromorphic co-processors for training deep neural networks (DNNs). However, device-level non-idealities are posing significant challenges. In this work we present a multi-ReRAM-based synaptic architecture with a counter-based arbitration scheme that shows significant promise. We present a 32x2 crossbar array comprising Pt/HfO2/Ti/TiN-based ReRAM devices with multi-level storage capability and bidirectional conductance response. We study the device characteristics in detail and model the conductance response. We show through simulations that an in-situ trained DNN with a multi-ReRAM synaptic architecture can perform handwritten digit classification task with high accuracies, only 2% lower than software simulations using floating point precision, despite the stochasticity, nonlinearity and large conductance change granularity associated with the devices. Moreover, we show that a network can achieve accuracies > 80% even with just binary ReRAM devices with this architecture.resistive random access memoryneuromorphic computingin-memory computingdeep neural networksmemorydevicetext::conference output::conference proceedings::conference paper