Learning Two-Input Linear and Nonlinear Analog Functions with a Simple Chemical System
The current biochemical information processing systems behave in a pre-determined manner because all features are defined during the design phase. To make such unconventional computing systems reusable and programmable for biomedical applications, adaptation, learning, and self-modification based on external stimuli would be highly desirable. However, so far, it has been too challenging to implement these in wet chemistries. In this paper we extend the chemical perceptron, a model previously proposed by the authors, to function as an analog instead of a binary system. The new analog asymmetric signal perceptron learns through feedback and supports Michaelis-Menten kinetics. The results show that our perceptron is able to learn linear and nonlinear (quadratic) functions of two inputs. To the best of our knowledge, it is the first simulated chemical system capable of doing so. The small number of species and reactions and their simplicity allows for a mapping to an actual wet implementation using DNA-strand displacement or deoxyribozymes. Our results are an important step toward actual biochemical systems that can learn and adapt.
KeywordsChemical perceptron analog perceptron supervised learning chemical computing RNMSE linear function quadratic function
Unable to display preview. Download preview PDF.
- 3.Haykin, S.: Neural networks and learning machines, 3rd edn. Pearson, New Jersey (2009)Google Scholar
- 6.Kim, J., Hopfield, J.J., Winfree, E.: Neural network computation by in vitro transcriptional circuits. In: Saul, L.K., Weiss, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems, vol. 17, pp. 681–688. MIT Press (2004)Google Scholar
- 10.Banda, P., Teuscher, C., Stefanovic, D.: Training an asymmetric signal perceptron through reinforcement in an artificial chemistry. Journal of the Royal Society Interface 11(93) (2014)Google Scholar
- 11.Moles, J., Banda, P., Teuscher, C.: Delay line as a chemical reaction network (under review). Parallel Processing Letters (2014)Google Scholar
- 12.Espenson, J.: Chemical kinetics and reaction mechanisms. McGraw-Hill, Singapore (1995)Google Scholar
- 13.Copeland, R.A.: Enzymes: A practical introduction to structure, mechanism, and data analysis, 2nd edn. John Wiley & Sons, Inc., New York (2002)Google Scholar
- 15.Rojas, R.: Neural networks: A systematic introduction. Springer, Berlin (1996)Google Scholar
- 18.Liu, J., Cao, Z., Lu, Y.: Functional nucleic acid sensors. Chemical Reviews 109(5), 1948–1998 (2009); PMID: 19301873Google Scholar