Axiomatic scalable neurocontroller analysis via the Shapley value
Standard
Axiomatic scalable neurocontroller analysis via the Shapley value. / Keinan, Alon; Sandbank, Ben; Hilgetag, Claus C; Meilijson, Isaac; Ruppin, Eytan.
In: ARTIF LIFE, Vol. 12, No. 3, 2006, p. 333-52.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Axiomatic scalable neurocontroller analysis via the Shapley value
AU - Keinan, Alon
AU - Sandbank, Ben
AU - Hilgetag, Claus C
AU - Meilijson, Isaac
AU - Ruppin, Eytan
PY - 2006
Y1 - 2006
N2 - One of the major challenges in the field of neurally driven evolved autonomous agents is deciphering the neural mechanisms underlying their behavior. Aiming at this goal, we have developed the multi-perturbation Shapley value analysis (MSA)--the first axiomatic and rigorous method for deducing causal function localization from multiple-perturbation data, substantially improving on earlier approaches. Based on fundamental concepts from game theory, the MSA provides a formal way of defining and quantifying the contributions of network elements, as well as the functional interactions between them. The previously presented versions of the MSA require full knowledge (or at least an approximation) of the network's performance under all possible multiple perturbations, limiting their applicability to systems with a small number of elements. This article focuses on presenting new scalable MSA variants, allowing for the analysis of large complex networks in an efficient manner, including large-scale neurocontrollers. The successful operation of the MSA along with the new variants is demonstrated in the analysis of several neurocontrollers solving a food foraging task, consisting of up to 100 neural elements.
AB - One of the major challenges in the field of neurally driven evolved autonomous agents is deciphering the neural mechanisms underlying their behavior. Aiming at this goal, we have developed the multi-perturbation Shapley value analysis (MSA)--the first axiomatic and rigorous method for deducing causal function localization from multiple-perturbation data, substantially improving on earlier approaches. Based on fundamental concepts from game theory, the MSA provides a formal way of defining and quantifying the contributions of network elements, as well as the functional interactions between them. The previously presented versions of the MSA require full knowledge (or at least an approximation) of the network's performance under all possible multiple perturbations, limiting their applicability to systems with a small number of elements. This article focuses on presenting new scalable MSA variants, allowing for the analysis of large complex networks in an efficient manner, including large-scale neurocontrollers. The successful operation of the MSA along with the new variants is demonstrated in the analysis of several neurocontrollers solving a food foraging task, consisting of up to 100 neural elements.
KW - Models, Statistical
KW - Neural Networks (Computer)
KW - Software
KW - User-Computer Interface
KW - Journal Article
KW - Research Support, Non-U.S. Gov't
U2 - 10.1162/artl.2006.12.3.333
DO - 10.1162/artl.2006.12.3.333
M3 - SCORING: Journal article
C2 - 16859444
VL - 12
SP - 333
EP - 352
JO - ARTIF LIFE
JF - ARTIF LIFE
SN - 1064-5462
IS - 3
ER -