Document Type
Article
Publication Date
1-1-2013
Subjects
Perceptrons, Chemistry -- Computer programs
Abstract
Autonomous learning implemented purely by means of a synthetic chemical system has not been previously realized. Learning promotes reusability and minimizes the system design to simple input-output specification. In this article we introduce a chemical perceptron, the first full-featured implementation of a perceptron in an artificial (simulated) chemistry. A perceptron is the simplest system capable of learning, inspired by the functioning of a biological neuron. Our artificial chemistry is deterministic and discrete-time, and follows Michaelis-Menten kinetics. We present two models, the weight-loop perceptron and the weight-race perceptron, which represent two possible strategies for a chemical implementation of linear integration and threshold. Both chemical perceptrons can successfully identify all 14 linearly separable two-input logic functions and maintain high robustness against rate-constant perturbations. We suggest that DNA strand displacement could, in principle, provide an implementation substrate for our model, allowing the chemical perceptron to perform reusable, programmable, and adaptable wet biochemical computing.
DOI
10.1162/ artl_a_00105
Persistent Identifier
http://archives.pdx.edu/ds/psu/9562
Citation Details
Banda, Peter, Christof Teuscher, and Matthew R. Lakin. "Online learning in a chemical perceptron." (2013).
Description
© 2013 Massachusetts Institute of Technology. A version of this paper with color figures is available online at http://dx.doi.org/10.1162/ artl_a_00105. Subscription required.
This research was funded by NSF grant 1028120.