TY - JOUR
T1 - Neurocontroller analysis via evolutionary network minimization
AU - Ganon, Zohar
AU - Keinan, Alon
AU - Ruppin, Eytan
PY - 2006
Y1 - 2006
N2 - This study presents a new evolutionary network minimization (ENM) algorithm. Neurocontroller minimization is beneficial for finding small parsimonious networks that permit a better understanding of their workings. The ENM algorithm is specifically geared to an evolutionary agents setup, as it does not require any explicit supervised training error, and is very easily incorporated in current evolutionary algorithms. ENM is based on a standard genetic algorithm with an additional step during reproduction in which synaptic connections are irreversibly eliminated. It receives as input a successfully evolved neurocontroller and aims to output a pruned neurocontroller, while maintaining the original fitness level. The small neurocontrollers produced by ENM provide upper bounds on the neurocontroller size needed to perform a given task successfully, and can provide for more effcient hardware implementations.
AB - This study presents a new evolutionary network minimization (ENM) algorithm. Neurocontroller minimization is beneficial for finding small parsimonious networks that permit a better understanding of their workings. The ENM algorithm is specifically geared to an evolutionary agents setup, as it does not require any explicit supervised training error, and is very easily incorporated in current evolutionary algorithms. ENM is based on a standard genetic algorithm with an additional step during reproduction in which synaptic connections are irreversibly eliminated. It receives as input a successfully evolved neurocontroller and aims to output a pruned neurocontroller, while maintaining the original fitness level. The small neurocontrollers produced by ENM provide upper bounds on the neurocontroller size needed to perform a given task successfully, and can provide for more effcient hardware implementations.
KW - Evolutionary agents
KW - Evolutionary algorithms
KW - Network minimization
KW - Neurocontroller analysis
KW - Synaptic pruning
UR - http://www.scopus.com/inward/record.url?scp=33746833985&partnerID=8YFLogxK
U2 - 10.1162/artl.2006.12.3.435
DO - 10.1162/artl.2006.12.3.435
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:33746833985
SN - 1064-5462
VL - 12
SP - 435
EP - 448
JO - Artificial Life
JF - Artificial Life
IS - 3
ER -