2023/11/02 by William Poole, Poole, William, Thomas E. Ouldridge +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Biological Physics (physics.bio-ph) #Computational Drug Discovery Methods #Emerging Technologies (cs.ET) #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Physical sciences #Gene Regulatory Network Analysis #Machine Learning (cs.LG) #Machine Learning in Materials Science #Molecular Networks (q-bio.MN) #Neural and Evolutionary Computing (cs.NE) #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2311.00975
openalex publication_date 2023/11/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.