Event-based Spiking Neural Networks for Object Detection: Datasets, Architectures, Learning Rules, and Implementation
Document Type
Article
Publication Date
1-1-2024
Abstract
Spiking Neural Networks (SNNs) represent a biologically inspired paradigm offering an energy-efficient alternative to conventional artificial neural networks (ANNs) for Computer Vision (CV) applications. This paper presents a systematic review of datasets, architectures, learning methods, implementation techniques and evaluation methodologies used in CV-based detection tasks using SNNs. Based on an analysis of 151 journal and conference articles, the review codifies: 1) the effectiveness of fully connected, convolutional, and recurrent architectures; 2) the performance of direct unsupervised, direct supervised, and indirect learning methods; and 3) the trade-offs in energy consumption, latency, and memory in neuromorphic hardware implementations. Key challenges in SNN training, hardware integration, and future directions for more advanced CV applications are also identified.
Identifier
85207733108 (Scopus)
Publication Title
IEEE Access
External Full Text Location
https://doi.org/10.1109/ACCESS.2024.3479968
e-ISSN
21693536
Recommended Citation
Iaboni, Craig and Abichandani, Pramod, "Event-based Spiking Neural Networks for Object Detection: Datasets, Architectures, Learning Rules, and Implementation" (2024). Faculty Publications. 834.
https://digitalcommons.njit.edu/fac_pubs/834
