We describe the initial phase of a research project to
develop an artificial life framework designed to
extract knowledge from large data sets with minimal
preparation or ramp-up time. In this phase, we evolved
an artificial life population with a new brain
architecture. The agents have sufficient intelligence
to discover patterns in data and to make survival
decisions based on those patterns. The species uses
diploid reproduction, Hebbian learning, and Kohonen
self-organizing maps, in combination with novel
techniques such as using pattern-rich data as the
environment and framing the data analysis as a survival
problem for artificial life. The first generation of
agents mastered the pattern discovery task well enough
to thrive. Evolution further adapted the agents to
their environment by making them a little more
pessimistic, and also by making their brains more
efficient.
%0 Journal Article
%1 debuitleir-wains-pattern-alife-2012
%A de Buitléir, Amy
%A Russell, Michael
%A Daly, Mark
%D 2012
%J Artificial Life
%K alife myown
%N 4
%P 399--423
%R 10.1162/artl_a_00074
%T Wains: A pattern-seeking artificial life species
%V 18
%X We describe the initial phase of a research project to
develop an artificial life framework designed to
extract knowledge from large data sets with minimal
preparation or ramp-up time. In this phase, we evolved
an artificial life population with a new brain
architecture. The agents have sufficient intelligence
to discover patterns in data and to make survival
decisions based on those patterns. The species uses
diploid reproduction, Hebbian learning, and Kohonen
self-organizing maps, in combination with novel
techniques such as using pattern-rich data as the
environment and framing the data analysis as a survival
problem for artificial life. The first generation of
agents mastered the pattern discovery task well enough
to thrive. Evolution further adapted the agents to
their environment by making them a little more
pessimistic, and also by making their brains more
efficient.
@article{debuitleir-wains-pattern-alife-2012,
abstract = {We describe the initial phase of a research project to
develop an artificial life framework designed to
extract knowledge from large data sets with minimal
preparation or ramp-up time. In this phase, we evolved
an artificial life population with a new brain
architecture. The agents have sufficient intelligence
to discover patterns in data and to make survival
decisions based on those patterns. The species uses
diploid reproduction, Hebbian learning, and Kohonen
self-organizing maps, in combination with novel
techniques such as using pattern-rich data as the
environment and framing the data analysis as a survival
problem for artificial life. The first generation of
agents mastered the pattern discovery task well enough
to thrive. Evolution further adapted the agents to
their environment by making them a little more
pessimistic, and also by making their brains more
efficient.},
added-at = {2012-07-27T17:02:41.000+0200},
author = {de Buitl{\'e}ir, Amy and Russell, Michael and Daly, Mark},
biburl = {https://www.bibsonomy.org/bibtex/241f0b3015c736523bd9a29430c599db2/mhwombat},
doi = {10.1162/artl_a_00074},
interhash = {e4072479bb4637d6e6479587b6aa5f00},
intrahash = {41f0b3015c736523bd9a29430c599db2},
journal = {Artificial Life},
keywords = {alife myown},
number = 4,
pages = {399--423},
timestamp = {2016-08-05T19:04:12.000+0200},
title = {Wains: {A} pattern-seeking artificial life species},
volume = 18,
year = 2012
}