Research ExplorerPublicationsAxiomatic scalable neurocontroller analysis via the Shapley ...

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

Keinan, A, Sandbank, B, Hilgetag, CC, Meilijson, I & Ruppin, E 2006, 'Axiomatic scalable neurocontroller analysis via the Shapley value', ARTIF LIFE, vol. 12, no. 3, pp. 333-52. https://doi.org/10.1162/artl.2006.12.3.333

APA

Keinan, A., Sandbank, B., Hilgetag, C. C., Meilijson, I., & Ruppin, E. (2006). Axiomatic scalable neurocontroller analysis via the Shapley value. ARTIF LIFE, 12(3), 333-52. https://doi.org/10.1162/artl.2006.12.3.333

Vancouver

Keinan A, Sandbank B, Hilgetag CC, Meilijson I, Ruppin E. Axiomatic scalable neurocontroller analysis via the Shapley value. ARTIF LIFE. 2006;12(3):333-52. https://doi.org/10.1162/artl.2006.12.3.333

Bibtex

@article{c50f44dc9ca24cd4a8b81f5b90bddc0d,
title = "Axiomatic scalable neurocontroller analysis via the Shapley value",
abstract = "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.",
keywords = "Models, Statistical, Neural Networks (Computer), Software, User-Computer Interface, Journal Article, Research Support, Non-U.S. Gov't",
author = "Alon Keinan and Ben Sandbank and Hilgetag, {Claus C} and Isaac Meilijson and Eytan Ruppin",
year = "2006",
doi = "10.1162/artl.2006.12.3.333",
language = "English",
volume = "12",
pages = "333--52",
journal = "ARTIF LIFE",
issn = "1064-5462",
publisher = "MIT Press",
number = "3",

}

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 -