Nanoscale Memristor‐Based Spike Timing‐Dependent Plasticity Learning in a Radix‐X Quantized Retinal Neural Network. Issue 20 (27th May 2022)

• Record Type: Journal Article
• Authors: Kim, Young Hwan; Eshraghian, Jason K.; Goo, Yong Sook; Cho, Kyoungrok
• Other Names: Lee Jae Shin guestEditor.; Yoon Sung‐Min guestEditor.
• Is Part Of: Physica status solidi. Volume 219:Issue 20(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-05-27
• Subjects: memristors -- retina -- spike timing-dependent plasticity -- spiking neural models; Solid state physics -- Periodicals; Solids -- Industrial applications -- Periodicals; 530.41
• DOI: 10.1002/pssa.202100798
• Languages: English
• ISSNs: 1862-6300

Abstract

Abstract : The human retina sends visual signals to the brain's visual cortex from photoreceptors (rod and cone cells) through various synaptic pathways and performs crucial early vision processing before signals are passed to higher brain regions. Herein, an artificial retina system implemented based on the leaky integrate‐and‐fire spiking neuron model is presented. The architecture of the proposed retina system consists of a multilayer convolutional neural network (CNN), and the system uses spike timing‐dependent plasticity (STDP) as a feedforward learning rule. In addition, the system integrates a feedback plasticity learning rule to expedite learning convergence. The system weights are implemented using nanoscale memristor arrays, taking on a constrained (radix‐X) range of conductance states. The proposed system produces an output image of 25 × 25 pixels, corresponding to the output retina ganglion cells that act as the interface between the retina and the visual cortex, using an input image of 100 × 100 pixels. Abstract : An artificial retina system is implemented based on the leaky integrate‐and‐fire spiking neural model. The architecture of the proposed retina system consists of a multilayer convolutional neural network (CNN), and the system uses spike timing‐dependent plasticity (STDP) as a feedforward learning rule. The system weights are implemented using nanoscale memristor arrays, taking the constrained (radix‐X) range of conductance states.