 |
    |
Evolution-In-Materio: Solving Machine Learning Classification Problems Using Materials
Maktuba Mohid1, Julian Francis Miller1, Simon L. Harding2, Gunnar Tufte2, Odd Rune Lykkebø3, Mark K. Massey3, and Michael C. Petty
1Department of Electronics, University of York, York, UK
mm1159@york.ac.uk
julian.miller@york.ac.uk
m.c.petty@durham.ac.uk
2Department of Computer and Information Science, Norwegian University of Science and Technology, 7491, Trondheim, Norway
slh@evolutioninmaterio.com
gunnart@idi.ntnu.no
3School of Engineering and Computing Sciences and Centre for Molecular and Nanoscale Electronics, Durham University, UK
lykkebo@idi.ntnu.no
m.k.massey@durham.ac.uk
Abstract. Evolution-in-materio (EIM) is a method that uses artificial evolution to exploit the properties of physical matter to solve computational problems without requiring a detailed understanding of such properties. EIM has so far been applied to very few computational problems. We show that using a purpose-built hardware platform called Mecobo, it is possible to evolve voltages and signals applied to physical materials to solve machine learning classification problems. This is the first time that EIM has been applied to such problems. We evaluate the approach on two standard datasets: Lenses and Iris. Comparing our technique with a well-known software-based evolutionary method indicates that EIM performs reasonably well. We suggest that EIM offers a promising new direction for evolutionary computation.
Keywords: Evolutionary algorithm, evolution-in-materio, material computation, evolvable hardware, machine learning, classification problem
LNCS 8672, p. 721 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014