Design and Implementation of a Flexible Neuromorphic Computing System for Affective Communication via Memristive Circuits

Abstract

Neuromorphic computing is expected to realize fast and energy-efficient artificial neural networks and address the inherent limitations of von Neumann architectures in dedicated communication applications. To realize this vision, we identify the existing challenges in neuromorphic computing and provide a specific solution from the perspectives of device, circuit, and system. At the device level, we fabricate a metal oxide-based memristor with high stability, low power, and good scalability, serving as the fundamental component of neuromorphic computing system. At the circuit level, the basic circuit units and necessary peripheral circuits are designed to realize efficient vector-matrix multiplication and different functions, including nonlinear activation operation, subtraction operation, added operation, etc. At the system level, a flexible neuromorphic computing system with a hardware-friendly training approach is proposed, it can perform affective communication with good trade-off between accuracy and time consumption. This study is expected to achieve the deep integration of nanotechnology, energy-efficient integrated circuits, and neuromorphic computing systems into communication applications.

MDGN: Circuit design of memristor‐based denoising autoencoder and gated recurrent unit network for lithium‐ion battery state of charge estimation

“…Traditional RNNs suffer from the gradient explosion or disappearance problem, which makes them fail to learn long-term dependencies [29]. Aiming to solve such gradient problems, the GRU network with a simple structure, few parameters, and fast execution is selected in this work.…”

TSDet: A new method for traffic sign detection based on YOLOv5‐SwinT

“…Furthermore, with the continuous improvement of AI hardware acceleration systems, the deployment of complex CNN networks has become feasible [34][35][36][37][38]. For instance, Gu et al [39] proposed a lightweight real-time traffic sign detection framework based on YOLOv4.…”

“…Furthermore, with the continuous improvement of AI hardware acceleration systems, the deployment of complex CNN networks has become feasible [34–38]. For instance, Gu et al.…”

Detecting tea tree pests in complex backgrounds using a hybrid architecture guided by transformers and multi‐scale attention mechanism

“…These capabilities have the potential to greatly benefit the challenging task of detecting small, camouflaged pests in intricate tea plantation environments. Notable research endeavors [14][15][16][17][18] have delved into the effectiveness of transformer-based architectures in addressing intricate challenges within the realms of affective computing and neuromorphic sensory-processing systems, showcasing the adaptability of these techniques to complex and nuanced data. Although these studies may not have a direct bearing on tea tree pest detection, they underscore the potential of transformer-based techniques in handling intricate and nuanced data, which aligns with our approach to tackling the challenges of detecting small targets in intricate tea plantation environments.…”