BPLC + NOSO: backpropagation of errors based on latency code with neurons that only spike once at most

BPLC + NOSO: backpropagation of errors based on latency code with neurons that only spike once at most

Abstract For mathematical completeness, we propose an error-backpropagation algorithm based on latency code (BPLC) with spiking neurons conforming to the spike–response model but allowed to spike once at most (NOSOs). BPLC is based on gradients derived without approximation unlike previous temporal...

Full description

Bibliographic Details
Main Authors: Seong Min Jin, Dohun Kim, Dong Hyung Yoo, Jason Eshraghian, Doo Seok Jeong
Format: Article
Language:English
Published: Springer 2023-02-01
Series:Complex & Intelligent Systems
Subjects:
Backpropagation based on latency code
Spiking neural networks
Minimum-latency pooling
Symmetric dual threshold
Online Access:https://doi.org/10.1007/s40747-023-00983-y

Internet

https://doi.org/10.1007/s40747-023-00983-y

Similar Items