Feedforward Chemical Neural Network: An In Silico Chemical System That Learns XOR

Authors

Drew Blount, Wild MeFollow
Peter Banda, University of LuxembourgFollow
Christof Teuscher, Portland State UniversityFollow
Darko Stefanovic, University of New MexicoFollow

Sponsor

This material is based upon work supported by the National Science Foundation under grants 1318833, 1518833, and 1518861.

Published In

Artificial Life

Document Type

Article

Publication Date

Summer 2017

Subjects

Adaptive learning, Neural networks -- Simulations, Chemical systems, Network topologies

Abstract

Inspired by natural biochemicals that perform complex information processing within living cells, we design and simulate a chemically implemented feedforward neural network, which learns by a novel chemical-reaction-based analogue of backpropagation. Our network is implemented in a simulated chemical system, where individual neurons are separated from each other by semipermeable cell-like membranes. Our compartmentalized, modular design allows a variety of network topologies to be constructed from the same building blocks. This brings us towards general-purpose, adaptive learning in chemico: wet machine learning in an embodied dynamical system.

Description

This is the publisher's final pdf. Article appears in Artificial Life (http://www.mitpressjournals.org/loi/artl) and is © 2017 by Massachusetts Institute of Technology. Article is available online at: http://dx.doi.org/10.1162/ARTL_a_00233

DOI

10.1162/ARTL_a_00233

Persistent Identifier

http://archives.pdx.edu/ds/psu/21085

Citation Details

Blount, D., Banda, P., Teuscher, C., & Stefanovic, D. (2017). Feedforward Chemical Neural Network: An In Silico Chemical System That Learns XOR. Artificial Life. Volume 23, Issue 3, p. 295-317.