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 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.
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
RN‐Net: Reservoir Nodes‐Enabled Neuromorphic Vision Sensing Network ; day:23 ; month:05 ; year:2024 ; extent:12
Advanced intelligent systems ; (23.05.2024) (gesamt 12)
- Urheber
- DOI
-
10.1002/aisy.202400265
- URN
-
urn:nbn:de:101:1-2405241419466.016582432867
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
14.08.2025, 10:50 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Yoo, Sangmnin
- Lee, Eric Yeu‐Jer
- Wang, Ziyu
- Wang, Xinxin
- Lu, Wei
Ähnliche Objekte (12)
Neuromorphic-enabled video-activated cell sorting
On-chip phonon-magnon reservoir for neuromorphic computing
Advanced Neuromorphic Applications Enabled by Synaptic Ion‐Gating Vertical Transistors
A Coupled Spintronics Neuromorphic Approach for High‐Performance Reservoir Computing
High-speed photonically-enabled ADCs with neuromorphic opto-electronic signal processing
Monolithic 2D Perovskites Enabled Artificial Photonic Synapses for Neuromorphic Vision Sensors
Multiplexed networks: reservoir computing with virtual and real nodes
2D Reconfigurable Memory Device Enabled by Defect Engineering for Multifunctional Neuromorphic Computing
Toward grouped-reservoir computing: organic neuromorphic vertical transistor with distributed reservoir states for efficient recognition and prediction
Binary‐Stochasticity‐Enabled Highly Efficient Neuromorphic Deep Learning Achieves Better‐than‐Software Accuracy
Heterosynaptic Plasticity and Neuromorphic Boolean Logic Enabled by Ferroelectric Polarization Modulated Schottky Diodes
Advanced Neuromorphic Applications Enabled by Synaptic Ion‐Gating Vertical Transistors (Adv. Sci. 27/2024)
Neuromorphic-enabled video-activated cell sorting
On-chip phonon-magnon reservoir for neuromorphic computing
Advanced Neuromorphic Applications Enabled by Synaptic Ion‐Gating Vertical Transistors
A Coupled Spintronics Neuromorphic Approach for High‐Performance Reservoir Computing
High-speed photonically-enabled ADCs with neuromorphic opto-electronic signal processing
Monolithic 2D Perovskites Enabled Artificial Photonic Synapses for Neuromorphic Vision Sensors
Multiplexed networks: reservoir computing with virtual and real nodes
2D Reconfigurable Memory Device Enabled by Defect Engineering for Multifunctional Neuromorphic Computing
Toward grouped-reservoir computing: organic neuromorphic vertical transistor with distributed reservoir states for efficient recognition and prediction
Binary‐Stochasticity‐Enabled Highly Efficient Neuromorphic Deep Learning Achieves Better‐than‐Software Accuracy
Heterosynaptic Plasticity and Neuromorphic Boolean Logic Enabled by Ferroelectric Polarization Modulated Schottky Diodes
Advanced Neuromorphic Applications Enabled by Synaptic Ion‐Gating Vertical Transistors (Adv. Sci. 27/2024)
Neuromorphic-enabled video-activated cell sorting
On-chip phonon-magnon reservoir for neuromorphic computing
Advanced Neuromorphic Applications Enabled by Synaptic Ion‐Gating Vertical Transistors
A Coupled Spintronics Neuromorphic Approach for High‐Performance Reservoir Computing
High-speed photonically-enabled ADCs with neuromorphic opto-electronic signal processing
Monolithic 2D Perovskites Enabled Artificial Photonic Synapses for Neuromorphic Vision Sensors
Multiplexed networks: reservoir computing with virtual and real nodes
2D Reconfigurable Memory Device Enabled by Defect Engineering for Multifunctional Neuromorphic Computing
Toward grouped-reservoir computing: organic neuromorphic vertical transistor with distributed reservoir states for efficient recognition and prediction
Binary‐Stochasticity‐Enabled Highly Efficient Neuromorphic Deep Learning Achieves Better‐than‐Software Accuracy
Heterosynaptic Plasticity and Neuromorphic Boolean Logic Enabled by Ferroelectric Polarization Modulated Schottky Diodes