Direct training high-performance deep spiking neural networks: a review of theories and methods

C Zhou, H Zhang, L Yu, Y Ye, Z Zhou… - Frontiers in …, 2024 - frontiersin.org
Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial
neural networks (ANNs), in virtue of their high biological plausibility, rich spatial-temporal …

Object detection with spiking neural networks on automotive event data

L Cordone, B Miramond… - 2022 International Joint …, 2022 - ieeexplore.ieee.org
Automotive embedded algorithms have very high constraints in terms of latency, accuracy
and power consumption. In this work, we propose to train spiking neural networks (SNNs) …

An electromagnetic perspective of artificial intelligence neuromorphic chips

EP Li, H Ma, M Ahmed, T Tao, Z Gu… - Electromagnetic …, 2023 - ieeexplore.ieee.org
The emergence of artificial intelligence has represented great potential in solving a wide
range of complex problems. However, traditional general-purpose chips based on von …

Eas-snn: End-to-end adaptive sampling and representation for event-based detection with recurrent spiking neural networks

Z Wang, Z Wang, H Li, L Qin, R Jiang, D Ma… - European Conference on …, 2024 - Springer
Event cameras, with their high dynamic range and temporal resolution, are ideally suited for
object detection in scenarios with motion blur and challenging lighting conditions. However …

Direct training high-performance spiking neural networks for object recognition and detection

H Zhang, Y Li, B He, X Fan, Y Wang… - Frontiers in …, 2023 - frontiersin.org
Introduction The spiking neural network (SNN) is a bionic model that is energy-efficient
when implemented on neuromorphic hardwares. The non-differentiability of the spiking …

Power efficient machine learning models deployment on edge IoT devices

A Fanariotis, T Orphanoudakis, K Kotrotsios… - Sensors, 2023 - mdpi.com
Computing has undergone a significant transformation over the past two decades, shifting
from a machine-based approach to a human-centric, virtually invisible service known as …

Neuromorphic computing for interactive robotics: a systematic review

M Aitsam, S Davies, A Di Nuovo - Ieee Access, 2022 - ieeexplore.ieee.org
Modelling functionalities of the brain in human-robot interaction contexts requires a real-time
understanding of how each part of a robot (motors, sensors, emotions, etc.) works and how …

Deep spiking residual shrinkage network for bearing fault diagnosis

Z Xu, Y Ma, Z Pan, X Zheng - IEEE Transactions on Cybernetics, 2022 - ieeexplore.ieee.org
Bearing fault diagnosis of electrical equipment has been a popular research area in recent
years because there are often some faults during continuous operation in production due to …

Spiking-diffusion: Vector quantized discrete diffusion model with spiking neural networks

M Liu, J Gan, R Wen, T Li, Y Chen, H Chen - arxiv preprint arxiv …, 2023 - arxiv.org
Spiking neural networks (SNNs) have tremendous potential for energy-efficient
neuromorphic chips due to their binary and event-driven architecture. SNNs have been …

Integration of neuromorphic AI in event-driven distributed digitized systems: Concepts and research directions

M Nilsson, O Schelén, A Lindgren, U Bodin… - Frontiers in …, 2023 - frontiersin.org
Increasing complexity and data-generation rates in cyber-physical systems and the
industrial Internet of things are calling for a corresponding increase in AI capabilities at the …