Autonomous Learning of Generative Models with Chemical Reaction Network Ensembles
Authors:
Preprint
Abstract
Can a micron sized sack of interacting molecules autonomously learn an internal model of a complex and fluctuating environment? We draw insights from control theory, machine learning theory, chemical reaction network theory, and statistical physics to develop a general architecture whereby a broad class of chemical systems can autonomously learn complex distributions. Our construction takes the form of a chemical implementation of machine learning's optimization workhorse: gradient descent on the relative entropy cost function. We show how this method can be applied to optimize any detailed balanced chemical reaction network and that the construction is capable of using hidden units to learn complex distributions. This result is then recast as a form of integral feedback control. Finally, due to our use of an explicit physical model of learning, we are able to derive thermodynamic costs and trade-offs associated to this process.Keywords
All Related Versions
This publication has 39 references indexed in Scilit:
- Stochastic approximations of higher-molecular by bi-molecular reactionsJournal of Mathematical Biology, 2023
- Perfect adaptation in biologyCell Systems, 2021
- Perfect and Near-Perfect Adaptation in Cell SignalingCell Systems, 2016
- Product-Form Stationary Distributions for Deficiency Zero Chemical Reaction NetworksBulletin of Mathematical Biology, 2010
- Sloppiness, robustness, and evolvability in systems biologyCurrent Opinion in Biotechnology, 2008
- Computation with finite stochastic chemical reaction networksNatural Computing, 2008
- Predictive coding: an account of the mirror neuron systemCognitive Processing, 2007
- Calcium Homeostasis and Parturient Hypocalcemia: An Integral Feedback PerspectiveJournal of Theoretical Biology, 2002
- A rigorous derivation of the chemical master equationPhysica A: Statistical Mechanics and its Applications, 1992
- The internal model principle of control theoryAutomatica, 1976