论文信息 - Optimized learning scheme for grayscale image recognition in a RRAM based analog neuromorphic system

Optimized learning scheme for grayscale image recognition in a RRAM based analog neuromorphic system

An analog neuromorphic system is developed based on the fabricated resistive switching memory array. A novel training scheme is proposed to optimize the performance of the analog system by utilizing the segmented synaptic behavior. The scheme is demonstrated on a grayscale image recognition. According to the experiment results, the optimized one improves learning accuracy from 77.83% to 91.32%, decreases energy consumption by more than two orders, and substantially boosts learning efficiency compared to the traditional training scheme.

[1] C. Wright,et al. Arithmetic and Biologically-Inspired Computing Using Phase-Change Materials , 2011, Advanced materials.

[2] E. Vianello,et al. Variability-tolerant Convolutional Neural Network for Pattern Recognition applications based on OxRAM synapses , 2014, 2014 IEEE International Electron Devices Meeting.

[3] J. Kim,et al. Neuromorphic speech systems using advanced ReRAM-based synapse , 2013, 2013 IEEE International Electron Devices Meeting.

[4] Tuo-Hung Hou,et al. 3D synaptic architecture with ultralow sub-10 fJ energy per spike for neuromorphic computation , 2014, 2014 IEEE International Electron Devices Meeting.

[5] Wei Yang Lu,et al. Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[6] Chi-Sang Poon,et al. Neuromorphic Silicon Neurons and Large-Scale Neural Networks: Challenges and Opportunities , 2011, Front. Neurosci..

[7] Jinfeng Kang,et al. A physical based analytic model of RRAM operation for circuit simulation , 2012, 2012 International Electron Devices Meeting.

[8] Shimeng Yu,et al. A neuromorphic visual system using RRAM synaptic devices with Sub-pJ energy and tolerance to variability: Experimental characterization and large-scale modeling , 2012, 2012 International Electron Devices Meeting.

[9] Shimeng Yu,et al. Ultra-low-energy three-dimensional oxide-based electronic synapses for implementation of robust high-accuracy neuromorphic computation systems. , 2014, ACS nano.