Pulse Propagation Networks: a neural network model that uses temporal coding by action potentials

Kevin Judd, K. Aihara

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

In this paper we study a model of a neural network that is fundamentally different from currently popular models. In this model we consider every action potential in the network, rather than average firing rates; this enables us to consider temporal coding by action potentials. This kind of model is not new, but we believe our results on computational ability to be new. We introduce a specific model, which we call a pulse propagation network (PPN), and consider this model from the point of view of information processing, as a dynamical system and as a computing machine. We show, in particular, that as a computing machine it can operate with real numbers and consequently it is of a class more powerful than a conventional Turing machine. In the process of this analysis, we develop a framework of concepts and techniques useful to understand and analyze these PPN.
Original languageEnglish
Pages (from-to)203-215
JournalNeural Networks
Volume6
DOIs
Publication statusPublished - 1993

Fingerprint

Neural Networks (Computer)
Action Potentials
Neural networks
Automatic Data Processing
Turing machines
Dynamical systems

Cite this

@article{6b274c0e80824128a3701b189eaa19b3,
title = "Pulse Propagation Networks: a neural network model that uses temporal coding by action potentials",
abstract = "In this paper we study a model of a neural network that is fundamentally different from currently popular models. In this model we consider every action potential in the network, rather than average firing rates; this enables us to consider temporal coding by action potentials. This kind of model is not new, but we believe our results on computational ability to be new. We introduce a specific model, which we call a pulse propagation network (PPN), and consider this model from the point of view of information processing, as a dynamical system and as a computing machine. We show, in particular, that as a computing machine it can operate with real numbers and consequently it is of a class more powerful than a conventional Turing machine. In the process of this analysis, we develop a framework of concepts and techniques useful to understand and analyze these PPN.",
author = "Kevin Judd and K. Aihara",
year = "1993",
doi = "10.1016/0893-6080(93)90017-Q",
language = "English",
volume = "6",
pages = "203--215",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier",

}

Pulse Propagation Networks: a neural network model that uses temporal coding by action potentials. / Judd, Kevin; Aihara, K.

In: Neural Networks, Vol. 6, 1993, p. 203-215.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Pulse Propagation Networks: a neural network model that uses temporal coding by action potentials

AU - Judd, Kevin

AU - Aihara, K.

PY - 1993

Y1 - 1993

N2 - In this paper we study a model of a neural network that is fundamentally different from currently popular models. In this model we consider every action potential in the network, rather than average firing rates; this enables us to consider temporal coding by action potentials. This kind of model is not new, but we believe our results on computational ability to be new. We introduce a specific model, which we call a pulse propagation network (PPN), and consider this model from the point of view of information processing, as a dynamical system and as a computing machine. We show, in particular, that as a computing machine it can operate with real numbers and consequently it is of a class more powerful than a conventional Turing machine. In the process of this analysis, we develop a framework of concepts and techniques useful to understand and analyze these PPN.

AB - In this paper we study a model of a neural network that is fundamentally different from currently popular models. In this model we consider every action potential in the network, rather than average firing rates; this enables us to consider temporal coding by action potentials. This kind of model is not new, but we believe our results on computational ability to be new. We introduce a specific model, which we call a pulse propagation network (PPN), and consider this model from the point of view of information processing, as a dynamical system and as a computing machine. We show, in particular, that as a computing machine it can operate with real numbers and consequently it is of a class more powerful than a conventional Turing machine. In the process of this analysis, we develop a framework of concepts and techniques useful to understand and analyze these PPN.

U2 - 10.1016/0893-6080(93)90017-Q

DO - 10.1016/0893-6080(93)90017-Q

M3 - Article

VL - 6

SP - 203

EP - 215

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

ER -