Dual coding and effects of global feedback in multilayered neural networks

Naoki Masuda; Kazuyuki Aihara

doi:10.1016/j.neucom.2004.01.019

Dual coding and effects of global feedback in multilayered neural networks

Naoki Masuda^*, Kazuyuki Aihara

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

Abstract

The synchronous firing code mode and the population rate code mode can alternatively appear in a single neural network to be dually used depending upon situations. In this paper, we examine by using multi-layered feedforward networks how the preferred coding mode switches as signals pass through layers. It is also shown that global feedback synchronizes neurons in the upstream layers.

Original language	English
Pages (from-to)	33-39
Number of pages	7
Journal	Neurocomputing
Volume	58-60
DOIs	https://doi.org/10.1016/j.neucom.2004.01.019
Publication status	Published - 2004 Jun
Externally published	Yes

Keywords

Feedback
Integrate-and-fire neurons
Rate coding
Synchrony

ASJC Scopus subject areas

Computer Science Applications
Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/j.neucom.2004.01.019

Cite this

@article{657d28b226ac42aba0753f2c8cea7ff0,

title = "Dual coding and effects of global feedback in multilayered neural networks",

abstract = "The synchronous firing code mode and the population rate code mode can alternatively appear in a single neural network to be dually used depending upon situations. In this paper, we examine by using multi-layered feedforward networks how the preferred coding mode switches as signals pass through layers. It is also shown that global feedback synchronizes neurons in the upstream layers.",

keywords = "Feedback, Integrate-and-fire neurons, Rate coding, Synchrony",

author = "Naoki Masuda and Kazuyuki Aihara",

note = "Funding Information: This study is partially supported by the Japan Society for the Promotion of Science and by a Grant-in-Aid No. 12210001 on priority areas (C) Advanced Brain Science Project and by the Advanced and Innovational Research program in Life Sciences from the Ministry of Education, Culture, Sports, Science, and Technology, the Japanese Government. ",

year = "2004",

month = jun,

doi = "10.1016/j.neucom.2004.01.019",

language = "English",

volume = "58-60",

pages = "33--39",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier",

}

TY - JOUR

T1 - Dual coding and effects of global feedback in multilayered neural networks

AU - Masuda, Naoki

AU - Aihara, Kazuyuki

N1 - Funding Information: This study is partially supported by the Japan Society for the Promotion of Science and by a Grant-in-Aid No. 12210001 on priority areas (C) Advanced Brain Science Project and by the Advanced and Innovational Research program in Life Sciences from the Ministry of Education, Culture, Sports, Science, and Technology, the Japanese Government.

PY - 2004/6

Y1 - 2004/6

N2 - The synchronous firing code mode and the population rate code mode can alternatively appear in a single neural network to be dually used depending upon situations. In this paper, we examine by using multi-layered feedforward networks how the preferred coding mode switches as signals pass through layers. It is also shown that global feedback synchronizes neurons in the upstream layers.

AB - The synchronous firing code mode and the population rate code mode can alternatively appear in a single neural network to be dually used depending upon situations. In this paper, we examine by using multi-layered feedforward networks how the preferred coding mode switches as signals pass through layers. It is also shown that global feedback synchronizes neurons in the upstream layers.

KW - Feedback

KW - Integrate-and-fire neurons

KW - Rate coding

KW - Synchrony

UR - http://www.scopus.com/inward/record.url?scp=2542435120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2542435120&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2004.01.019

DO - 10.1016/j.neucom.2004.01.019

M3 - Article

AN - SCOPUS:2542435120

SN - 0925-2312

VL - 58-60

SP - 33

EP - 39

JO - Neurocomputing

JF - Neurocomputing

ER -

Dual coding and effects of global feedback in multilayered neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this