TY - GEN
T1 - A Dynamical Biomolecular Neural Network
AU - Moorman, Andrew
AU - Samaniego, Christian Cuba
AU - Maley, Carlo
AU - Weiss, Ron
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - While much of synthetic biology was founded on the creation of reusable, standardized parts, there is now a growing interest in synthetic networks which can compute unique, specially-designed functions in order to recognize patterns or classify cells in-vivo. While artificial neural networks (ANNs) have long provided a mature mathematical framework to address this problem in-silico, their implementation becomes much more challenging in living systems. In this work, we propose a Biomolecular Neural Network (BNN), a dynamical chemical reaction network which faithfully implements ANN computations and which is unconditionally stable with respect to its parameters when composed into deeper networks. Our implementation emphasizes the usefulness of molecular sequestration for achieving negative weight values and a nonlinear activation function in its elemental unit, a biomolecular perceptron. We then discuss the application of BNNs to linear and nonlinear classification tasks, and draw analogies to other major concepts in modern machine learning research.
AB - While much of synthetic biology was founded on the creation of reusable, standardized parts, there is now a growing interest in synthetic networks which can compute unique, specially-designed functions in order to recognize patterns or classify cells in-vivo. While artificial neural networks (ANNs) have long provided a mature mathematical framework to address this problem in-silico, their implementation becomes much more challenging in living systems. In this work, we propose a Biomolecular Neural Network (BNN), a dynamical chemical reaction network which faithfully implements ANN computations and which is unconditionally stable with respect to its parameters when composed into deeper networks. Our implementation emphasizes the usefulness of molecular sequestration for achieving negative weight values and a nonlinear activation function in its elemental unit, a biomolecular perceptron. We then discuss the application of BNNs to linear and nonlinear classification tasks, and draw analogies to other major concepts in modern machine learning research.
UR - http://www.scopus.com/inward/record.url?scp=85082480030&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082480030&partnerID=8YFLogxK
U2 - 10.1109/CDC40024.2019.9030122
DO - 10.1109/CDC40024.2019.9030122
M3 - Conference contribution
AN - SCOPUS:85082480030
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 1797
EP - 1802
BT - 2019 IEEE 58th Conference on Decision and Control, CDC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 58th IEEE Conference on Decision and Control, CDC 2019
Y2 - 11 December 2019 through 13 December 2019
ER -