Direct training high-performance spiking neural networks for object recognition and detection
IntroductionThe spiking neural network (SNN) is a bionic model that is energy-efficient when implemented on neuromorphic hardwares. The non-differentiability of the spiking signals and the complicated neural dynamics make direct training of high-performance SNNs a great challenge. There are numerous...
Main Authors: | Hong Zhang, Yang Li, Bin He, Xiongfei Fan, Yue Wang, Yu Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-08-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1229951/full |
Similar Items
-
On-FPGA Spiking Neural Networks for End-to-End Neural Decoding
by: Gianluca Leone, et al.
Published: (2023-01-01) -
DY-RetinaNet Based Identification of Common Species at Beehive Nest Gates
by: Xianming Hu, et al.
Published: (2022-06-01) -
Dynamic Anchor: A Feature-Guided Anchor Strategy for Object Detection
by: Xing Liu, et al.
Published: (2022-05-01) -
An All-MRR-Based Photonic Spiking Neural Network for Spike Sequence Learning
by: Yanan Han, et al.
Published: (2022-02-01) -
Implementation of Field-Programmable Gate Array Platform for Object Classification Tasks Using Spike-Based Backpropagated Deep Convolutional Spiking Neural Networks
by: Vijay Kakani, et al.
Published: (2023-06-01)