Excellent Pattern Recognition Accuracy of Neural Networks Using Hybrid Synapses and Complementary Training

Abstract

To overcome the performance degradation in hardware neural networks (NNs) with non-ideal synapse devices, we proposed a novel neuromorphic architecture with both TiO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">x</sub> -based interfacial RRAM and CBRAM-based filamentary RRAM for highly accurate NN training and long-term inference reliability. We used a threshold-triggered training scheme, in which interfacial and filamentary RRAMs were programmed in a complementary fashion. This took advantage of the long retention time of the filamentary RRAM and the high-resolution, symmetric weight update in the interfacial RRAM. Additional evaluation of device parameters, such as linearity, precision, variation, and retention time, was conducted. An excellent pattern recognition accuracy of ~97% was achieved during training with the MNIST dataset. Thus, reliable inference accuracy after training was maintained using the filamentary RRAM.