TY - JOUR
T1 - Identifying regulation with adversarial surrogates
AU - Teichner, Ron
AU - Shomar, Aseel
AU - Barak, Omri
AU - Brenner, Naama
AU - Marom, Shimon
AU - Meir, Ron
AU - Eytan, Danny
N1 - Publisher Copyright:
Copyright © 2023 the Author(s).
PY - 2023/3/15
Y1 - 2023/3/15
N2 - Homeostasis, the ability to maintain a relatively constant internal environment in the face of perturbations, is a hallmark of biological systems. It is believed that this constancy is achieved through multiple internal regulation and control processes. Given observations of a system, or even a detailed model of one, it is both valuable and extremely challenging to extract the control objectives of the homeostatic mechanisms. In this work, we develop a robust data-driven method to identify these objectives, namely to understand: “what does the system care about?”. We propose an algorithm, Identifying Regulation with Adversarial Surrogates (IRAS), that receives an array of temporal measurements of the system and outputs a candidate for the control objective, expressed as a combination of observed variables. IRAS is an iterative algorithm consisting of two competing players. The first player, realized by an artificial deep neural network, aims to minimize a measure of invariance we refer to as the coefficient of regulation. The second player aims to render the task of the first player more difficult by forcing it to extract information about the temporal structure of the data, which is absent from similar “surrogate” data. We test the algorithm on four synthetic and one natural data set, demonstrating excellent empirical results. Interestingly, our approach can also be used to extract conserved quantities, e.g., energy and momentum, in purely physical systems, as we demonstrate empirically.
AB - Homeostasis, the ability to maintain a relatively constant internal environment in the face of perturbations, is a hallmark of biological systems. It is believed that this constancy is achieved through multiple internal regulation and control processes. Given observations of a system, or even a detailed model of one, it is both valuable and extremely challenging to extract the control objectives of the homeostatic mechanisms. In this work, we develop a robust data-driven method to identify these objectives, namely to understand: “what does the system care about?”. We propose an algorithm, Identifying Regulation with Adversarial Surrogates (IRAS), that receives an array of temporal measurements of the system and outputs a candidate for the control objective, expressed as a combination of observed variables. IRAS is an iterative algorithm consisting of two competing players. The first player, realized by an artificial deep neural network, aims to minimize a measure of invariance we refer to as the coefficient of regulation. The second player aims to render the task of the first player more difficult by forcing it to extract information about the temporal structure of the data, which is absent from similar “surrogate” data. We test the algorithm on four synthetic and one natural data set, demonstrating excellent empirical results. Interestingly, our approach can also be used to extract conserved quantities, e.g., energy and momentum, in purely physical systems, as we demonstrate empirically.
KW - artificial neural networks
KW - biological control
KW - biological regulation
KW - computational biology
KW - data analysis
KW - Algorithms
KW - Homeostasis
UR - http://www.scopus.com/inward/record.url?scp=85150396470&partnerID=8YFLogxK
U2 - 10.1073/pnas.2216805120
DO - 10.1073/pnas.2216805120
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 36920920
AN - SCOPUS:85150396470
SN - 0027-8424
VL - 120
SP - e2216805120
JO - Proceedings of the National Academy of Sciences of the United States of America
JF - Proceedings of the National Academy of Sciences of the United States of America
IS - 12
M1 - e2216805120
ER -