Time dependent classification of features with a nonlinear, dynamic network

Dissertation

Ari Vepsäläinen

Research output: ThesisDissertationCollection of Articles

Abstract

Temporally varying classification by a dynamic classifier network is introduced. The dynamic classifier network consists of several independent nonlinear classifiers in parallel. The subclassifiers adapt to the measurements with a variety of adaptation rates. The output of the classifier network can be calculated as a weighted sum of the outputs of each subclassifier. Two methods to optimize the weighting are given. However, even a simple weighting function gives reasonable results. The network might be considered as a temporal associative memory. Because of nonlinearities and the ensuing chaos the behavior of the network can be very complicated. Algorithms to calculate the fractal and correlation dimension are also given. With these dimensions one can estimate how complicated the behavior of a system is and how many parameters are needed to describe its behavior. An extension of geodesic distance transform, called distance transform in curved space, is also presented. This transform can, for example, be used to model dynamic decision manifolds. Some new properties of fractals are also presented. These properties can be utilized efficiently when defining the Lyapunov exponents and the basins of attraction for maps. The methods presented have several application areas.
Original languageEnglish
QualificationDoctor Degree
Awarding Institution
  • Helsinki University of Technology
Award date20 Dec 1991
Place of PublicationEspoo
Publisher
Print ISBNs951-38-4061-1
Publication statusPublished - 1991
MoE publication typeG5 Doctoral dissertation (article)

Fingerprint

Classifiers
Fractals
Chaos theory
Dynamic models
Data storage equipment

Keywords

  • neural networks
  • classification
  • nonlinear network analysis

Cite this

Vepsäläinen, A. (1991). Time dependent classification of features with a nonlinear, dynamic network: Dissertation. Espoo: VTT Technical Research Centre of Finland.
Vepsäläinen, Ari. / Time dependent classification of features with a nonlinear, dynamic network : Dissertation. Espoo : VTT Technical Research Centre of Finland, 1991. 158 p.
@phdthesis{3bade6ca44524ee98500e2fe8538801e,
title = "Time dependent classification of features with a nonlinear, dynamic network: Dissertation",
abstract = "Temporally varying classification by a dynamic classifier network is introduced. The dynamic classifier network consists of several independent nonlinear classifiers in parallel. The subclassifiers adapt to the measurements with a variety of adaptation rates. The output of the classifier network can be calculated as a weighted sum of the outputs of each subclassifier. Two methods to optimize the weighting are given. However, even a simple weighting function gives reasonable results. The network might be considered as a temporal associative memory. Because of nonlinearities and the ensuing chaos the behavior of the network can be very complicated. Algorithms to calculate the fractal and correlation dimension are also given. With these dimensions one can estimate how complicated the behavior of a system is and how many parameters are needed to describe its behavior. An extension of geodesic distance transform, called distance transform in curved space, is also presented. This transform can, for example, be used to model dynamic decision manifolds. Some new properties of fractals are also presented. These properties can be utilized efficiently when defining the Lyapunov exponents and the basins of attraction for maps. The methods presented have several application areas.",
keywords = "neural networks, classification, nonlinear network analysis",
author = "Ari Veps{\"a}l{\"a}inen",
note = "Project code: TIK1007",
year = "1991",
language = "English",
isbn = "951-38-4061-1",
series = "Publications / Technical Research Centre of Finland",
publisher = "VTT Technical Research Centre of Finland",
number = "83",
address = "Finland",
school = "Helsinki University of Technology",

}

Vepsäläinen, A 1991, 'Time dependent classification of features with a nonlinear, dynamic network: Dissertation', Doctor Degree, Helsinki University of Technology, Espoo.

Time dependent classification of features with a nonlinear, dynamic network : Dissertation. / Vepsäläinen, Ari.

Espoo : VTT Technical Research Centre of Finland, 1991. 158 p.

Research output: ThesisDissertationCollection of Articles

TY - THES

T1 - Time dependent classification of features with a nonlinear, dynamic network

T2 - Dissertation

AU - Vepsäläinen, Ari

N1 - Project code: TIK1007

PY - 1991

Y1 - 1991

N2 - Temporally varying classification by a dynamic classifier network is introduced. The dynamic classifier network consists of several independent nonlinear classifiers in parallel. The subclassifiers adapt to the measurements with a variety of adaptation rates. The output of the classifier network can be calculated as a weighted sum of the outputs of each subclassifier. Two methods to optimize the weighting are given. However, even a simple weighting function gives reasonable results. The network might be considered as a temporal associative memory. Because of nonlinearities and the ensuing chaos the behavior of the network can be very complicated. Algorithms to calculate the fractal and correlation dimension are also given. With these dimensions one can estimate how complicated the behavior of a system is and how many parameters are needed to describe its behavior. An extension of geodesic distance transform, called distance transform in curved space, is also presented. This transform can, for example, be used to model dynamic decision manifolds. Some new properties of fractals are also presented. These properties can be utilized efficiently when defining the Lyapunov exponents and the basins of attraction for maps. The methods presented have several application areas.

AB - Temporally varying classification by a dynamic classifier network is introduced. The dynamic classifier network consists of several independent nonlinear classifiers in parallel. The subclassifiers adapt to the measurements with a variety of adaptation rates. The output of the classifier network can be calculated as a weighted sum of the outputs of each subclassifier. Two methods to optimize the weighting are given. However, even a simple weighting function gives reasonable results. The network might be considered as a temporal associative memory. Because of nonlinearities and the ensuing chaos the behavior of the network can be very complicated. Algorithms to calculate the fractal and correlation dimension are also given. With these dimensions one can estimate how complicated the behavior of a system is and how many parameters are needed to describe its behavior. An extension of geodesic distance transform, called distance transform in curved space, is also presented. This transform can, for example, be used to model dynamic decision manifolds. Some new properties of fractals are also presented. These properties can be utilized efficiently when defining the Lyapunov exponents and the basins of attraction for maps. The methods presented have several application areas.

KW - neural networks

KW - classification

KW - nonlinear network analysis

M3 - Dissertation

SN - 951-38-4061-1

T3 - Publications / Technical Research Centre of Finland

PB - VTT Technical Research Centre of Finland

CY - Espoo

ER -

Vepsäläinen A. Time dependent classification of features with a nonlinear, dynamic network: Dissertation. Espoo: VTT Technical Research Centre of Finland, 1991. 158 p.