Learning at the crossroads of biology and computation

Author

Paredis, Jan

Author_Institution

RIKS/MATRIKS, Maastricht, Netherlands

fYear

1995

fDate

29-31 May 1995

Firstpage

56

Lastpage

63

Abstract

Discusses various avenues for exploiting biological learning mechanisms within machine learning. Special attention is given to the following issues: (a) the reasons for the wide variety of biological learning mechanisms; (b) the relation between lifetime and genetic learning; (c) a description of the driving forces of genetic learning and their use in evolutionary computation. Various symbolic machine learning and reasoning techniques can be used to complement (genetic and/or neural) sub-symbolic learning. A first approach uses symbolic induction for explaining the behavior of (genetically evolved) neural nets. Next, a general framework for the use of (symbolic) domain knowledge during genetic learning is introduced

Keywords

brain models; evolution (biological); learning (artificial intelligence); neural nets; neurophysiology; biological learning mechanisms; computation; evolutionary computation; genetic learning; genetically evolved neural nets; lifetime; machine learning; neural subsymbolic learning; symbolic domain knowledge; symbolic induction; symbolic machine learning; symbolic reasoning; Animals; Biology computing; Birds; Evolution (biology); Evolutionary computation; Genetics; Learning systems; Machine learning; Machine learning algorithms; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligence in Neural and Biological Systems, 1995. INBS'95, Proceedings., First International Symposium on

Conference_Location

Herndon, VA

Print_ISBN

0-8186-7116-5

Type

conf

DOI

10.1109/INBS.1995.404279

Filename

404279