Staged training of Neocognitron by evolutionary algorithms

Z. Pan; T. Sabisch; R.G. Adams; H. Bolouri

doi:10.1109/CEC.1999.785515

Staged training of Neocognitron by evolutionary algorithms

Z. Pan, T. Sabisch, R.G. Adams, H. Bolouri

Centre for Computer Science and Informatics Research

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Citations (Scopus)

30 Downloads (Pure)

Abstract

The Neocognitron, inspired by the mammalian visual system, is a complex neural network with numerous parameters and weights which should be trained in order to utilise it for pattern recognition. However, it is not easy to optimise these parameters and weights by gradient decent algorithms. In this paper, we present a staged training approach using evolutionary algorithms. The experiments demonstrate that evolutionary algorithms can successfully train the Neocognitron to perform image recognition on real world problems.

Original language	English
Title of host publication	In: Procs of the 1999 Congress on Evolutionary Computation (CEC'99) Vol. 3
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1965-1972
ISBN (Print)	0780355369
DOIs	https://doi.org/10.1109/CEC.1999.785515
Publication status	Published - 1999

Access to Document

10.1109/CEC.1999.785515

901702.pdf

Cite this

@inproceedings{e460cbc836564f2db624b42018a580d6,

title = "Staged training of Neocognitron by evolutionary algorithms",

abstract = "The Neocognitron, inspired by the mammalian visual system, is a complex neural network with numerous parameters and weights which should be trained in order to utilise it for pattern recognition. However, it is not easy to optimise these parameters and weights by gradient decent algorithms. In this paper, we present a staged training approach using evolutionary algorithms. The experiments demonstrate that evolutionary algorithms can successfully train the Neocognitron to perform image recognition on real world problems.",

author = "Z. Pan and T. Sabisch and R.G. Adams and H. Bolouri",

year = "1999",

doi = "10.1109/CEC.1999.785515",

language = "English",

isbn = "0780355369",

pages = "1965--1972",

booktitle = "In: Procs of the 1999 Congress on Evolutionary Computation (CEC'99) Vol. 3",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

TY - GEN

T1 - Staged training of Neocognitron by evolutionary algorithms

AU - Pan, Z.

AU - Sabisch, T.

AU - Adams, R.G.

AU - Bolouri, H.

PY - 1999

Y1 - 1999

N2 - The Neocognitron, inspired by the mammalian visual system, is a complex neural network with numerous parameters and weights which should be trained in order to utilise it for pattern recognition. However, it is not easy to optimise these parameters and weights by gradient decent algorithms. In this paper, we present a staged training approach using evolutionary algorithms. The experiments demonstrate that evolutionary algorithms can successfully train the Neocognitron to perform image recognition on real world problems.

AB - The Neocognitron, inspired by the mammalian visual system, is a complex neural network with numerous parameters and weights which should be trained in order to utilise it for pattern recognition. However, it is not easy to optimise these parameters and weights by gradient decent algorithms. In this paper, we present a staged training approach using evolutionary algorithms. The experiments demonstrate that evolutionary algorithms can successfully train the Neocognitron to perform image recognition on real world problems.

U2 - 10.1109/CEC.1999.785515

DO - 10.1109/CEC.1999.785515

M3 - Conference contribution

SN - 0780355369

SP - 1965

EP - 1972

BT - In: Procs of the 1999 Congress on Evolutionary Computation (CEC'99) Vol. 3

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Staged training of Neocognitron by evolutionary algorithms

Abstract

Access to Document

Fingerprint

Cite this