RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing Network

Neuromorphic computing systems promise high energy efficiency and low latency. In particular, when integrated with neuromorphic sensors, they can be used to produce intelligent systems for a broad range of applications. An event‐based camera is such a neuromorphic sensor, inspired by the sparse and...

Full description

Saved in:
Bibliographic Details
Main Authors: Sangmnin Yoo, Eric Yeu‐Jer Lee, Ziyu Wang, Xinxin Wang, Wei D. Lu
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Advanced Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1002/aisy.202400265
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850133131303059456
author Sangmnin Yoo
Eric Yeu‐Jer Lee
Ziyu Wang
Xinxin Wang
Wei D. Lu
author_facet Sangmnin Yoo
Eric Yeu‐Jer Lee
Ziyu Wang
Xinxin Wang
Wei D. Lu
author_sort Sangmnin Yoo
collection DOAJ
description Neuromorphic computing systems promise high energy efficiency and low latency. In particular, when integrated with neuromorphic sensors, they can be used to produce intelligent systems for a broad range of applications. An event‐based camera is such a neuromorphic sensor, inspired by the sparse and asynchronous spike representation of the biological visual system. However, processing the event data requires either using expensive feature descriptors to transform spikes into frames, or using spiking neural networks (SNNs) that are expensive to train. In this work, a neural network architecture is proposed, reservoir nodes‐enabled neuromorphic vision sensing network (RN‐Net), based on dynamic temporal encoding by on‐sensor reservoirs and simple deep neural network (DNN) blocks. The reservoir nodes enable efficient temporal processing of asynchronous events by leveraging the native dynamics of the node devices, while the DNN blocks enable spatial feature processing. Combining these blocks in a hierarchical structure, the RN‐Net offers efficient processing for both local and global spatiotemporal features. RN‐Net executes dynamic vision tasks created by event‐based cameras at the highest accuracy reported to date at one order of magnitude smaller network size. The use of simple DNN and standard backpropagation‐based training rules further reduces implementation and training costs.
format Article
id doaj-art-b49aa02b9add4e6e8fbe455abadbcccd
institution OA Journals
issn 2640-4567
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Advanced Intelligent Systems
spelling doaj-art-b49aa02b9add4e6e8fbe455abadbcccd2025-08-20T02:32:04ZengWileyAdvanced Intelligent Systems2640-45672024-12-01612n/an/a10.1002/aisy.202400265RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing NetworkSangmnin Yoo0Eric Yeu‐Jer Lee1Ziyu Wang2Xinxin Wang3Wei D. Lu4Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor 48109 MI USADepartment of Electrical Engineering and Computer Science University of Michigan Ann Arbor 48109 MI USADepartment of Electrical Engineering and Computer Science University of Michigan Ann Arbor 48109 MI USADepartment of Electrical Engineering and Computer Science University of Michigan Ann Arbor 48109 MI USADepartment of Electrical Engineering and Computer Science University of Michigan Ann Arbor 48109 MI USANeuromorphic computing systems promise high energy efficiency and low latency. In particular, when integrated with neuromorphic sensors, they can be used to produce intelligent systems for a broad range of applications. An event‐based camera is such a neuromorphic sensor, inspired by the sparse and asynchronous spike representation of the biological visual system. However, processing the event data requires either using expensive feature descriptors to transform spikes into frames, or using spiking neural networks (SNNs) that are expensive to train. In this work, a neural network architecture is proposed, reservoir nodes‐enabled neuromorphic vision sensing network (RN‐Net), based on dynamic temporal encoding by on‐sensor reservoirs and simple deep neural network (DNN) blocks. The reservoir nodes enable efficient temporal processing of asynchronous events by leveraging the native dynamics of the node devices, while the DNN blocks enable spatial feature processing. Combining these blocks in a hierarchical structure, the RN‐Net offers efficient processing for both local and global spatiotemporal features. RN‐Net executes dynamic vision tasks created by event‐based cameras at the highest accuracy reported to date at one order of magnitude smaller network size. The use of simple DNN and standard backpropagation‐based training rules further reduces implementation and training costs.https://doi.org/10.1002/aisy.202400265event‐based cameramemristorneuromorphicreservoir computingSNN
spellingShingle Sangmnin Yoo
Eric Yeu‐Jer Lee
Ziyu Wang
Xinxin Wang
Wei D. Lu
RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing Network
Advanced Intelligent Systems
event‐based camera
memristor
neuromorphic
reservoir computing
SNN
title RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing Network
title_full RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing Network
title_fullStr RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing Network
title_full_unstemmed RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing Network
title_short RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing Network
title_sort rn net reservoir nodes enabled neuromorphic vision sensing network
topic event‐based camera
memristor
neuromorphic
reservoir computing
SNN
url https://doi.org/10.1002/aisy.202400265
work_keys_str_mv AT sangmninyoo rnnetreservoirnodesenabledneuromorphicvisionsensingnetwork
AT ericyeujerlee rnnetreservoirnodesenabledneuromorphicvisionsensingnetwork
AT ziyuwang rnnetreservoirnodesenabledneuromorphicvisionsensingnetwork
AT xinxinwang rnnetreservoirnodesenabledneuromorphicvisionsensingnetwork
AT weidlu rnnetreservoirnodesenabledneuromorphicvisionsensingnetwork