Genesis of organic computing systems: coupling evolution and learning

Publikation: Bidrag til bog/antologi/rapport › Bidrag til bog/antologi › Forskning › fagfællebedømt

Standard

Genesis of organic computing systems : coupling evolution and learning. / Igel, Christian; Sendhoff, Bernhard.

Organic computing. 2008. s. 141-166 (Understanding Complex Systems).

Publikation: Bidrag til bog/antologi/rapport › Bidrag til bog/antologi › Forskning › fagfællebedømt

Harvard

Igel, C & Sendhoff, B 2008, Genesis of organic computing systems: coupling evolution and learning. i Organic computing. Understanding Complex Systems, s. 141-166. https://doi.org/10.1007/978-3-540-77657-4_7

APA

Igel, C., & Sendhoff, B. (2008). Genesis of organic computing systems: coupling evolution and learning. I Organic computing (s. 141-166). Understanding Complex Systems https://doi.org/10.1007/978-3-540-77657-4_7

Vancouver

Igel C, Sendhoff B. Genesis of organic computing systems: coupling evolution and learning. I Organic computing. 2008. s. 141-166. (Understanding Complex Systems). https://doi.org/10.1007/978-3-540-77657-4_7

Author

Igel, Christian ; Sendhoff, Bernhard. / Genesis of organic computing systems : coupling evolution and learning. Organic computing. 2008. s. 141-166 (Understanding Complex Systems).

Bibtex

@inbook{e97139cec00142eaa78b03789a6b5c31,
title = "Genesis of organic computing systems: coupling evolution and learning",
abstract = "Organic computing calls for efficient adaptive systems in which flexibility is not traded in against stability and robustness. Such systems have to be specialized in the sense that they are biased towards solving instances from certain problem classes, namely those problems they may face in their environment. Nervous systems are perfect examples. Their specialization stems from evolution and development. In organic computing, simulated evolutionary structure optimization can create artificial neural networks for particular environments. In this chapter, trends and recent results in combining evolutionary and neural computation are reviewed. The emphasis is put on the influence of evolution evolution and development on the structure of neural systems. It is demonstrated how neural structures can be evolved that efficiently learn solutions for problems from a particular problem class. Simple examples of systems that {"}learn to learn{"} as well as technical solutions for the design design of turbomachinery components are presented.",
author = "Christian Igel and Bernhard Sendhoff",
year = "2008",
doi = "10.1007/978-3-540-77657-4_7",
language = "English",
isbn = "978-3-540-77656-7",
series = "Understanding Complex Systems",
publisher = "Springer",
pages = "141--166",
booktitle = "Organic computing",

}

RIS

TY - CHAP

T1 - Genesis of organic computing systems

T2 - coupling evolution and learning

AU - Igel, Christian

AU - Sendhoff, Bernhard

PY - 2008

Y1 - 2008

N2 - Organic computing calls for efficient adaptive systems in which flexibility is not traded in against stability and robustness. Such systems have to be specialized in the sense that they are biased towards solving instances from certain problem classes, namely those problems they may face in their environment. Nervous systems are perfect examples. Their specialization stems from evolution and development. In organic computing, simulated evolutionary structure optimization can create artificial neural networks for particular environments. In this chapter, trends and recent results in combining evolutionary and neural computation are reviewed. The emphasis is put on the influence of evolution evolution and development on the structure of neural systems. It is demonstrated how neural structures can be evolved that efficiently learn solutions for problems from a particular problem class. Simple examples of systems that "learn to learn" as well as technical solutions for the design design of turbomachinery components are presented.

AB - Organic computing calls for efficient adaptive systems in which flexibility is not traded in against stability and robustness. Such systems have to be specialized in the sense that they are biased towards solving instances from certain problem classes, namely those problems they may face in their environment. Nervous systems are perfect examples. Their specialization stems from evolution and development. In organic computing, simulated evolutionary structure optimization can create artificial neural networks for particular environments. In this chapter, trends and recent results in combining evolutionary and neural computation are reviewed. The emphasis is put on the influence of evolution evolution and development on the structure of neural systems. It is demonstrated how neural structures can be evolved that efficiently learn solutions for problems from a particular problem class. Simple examples of systems that "learn to learn" as well as technical solutions for the design design of turbomachinery components are presented.

U2 - 10.1007/978-3-540-77657-4_7

DO - 10.1007/978-3-540-77657-4_7

M3 - Book chapter

AN - SCOPUS:54849423676

SN - 978-3-540-77656-7

T3 - Understanding Complex Systems

SP - 141

EP - 166

BT - Organic computing

ER -

ID: 168323322