Solving binary classification problems with carbon nanotube / liquid crystal composites and evolutionary algorithms

This paper presents a series of experiments demonstrating the capacity of single-walled carbon-nanotube (SWCNT)/liquid crystal (LC) mixtures to be trained by evolutionary algorithms to act as classifiers on linear and nonlinear binary datasets. The training process is formulated as an optimisation problem with hardware in the loop. The liquid SWCNT/LC samples used here are un-configured and with nonlinear current-voltage relationship, thus presenting a potential for being evolved. The nature of the problem means that derivative-free stochastic search algorithms are required. Results presented here are based on differential evolution (DE) and particle swarm optimisation (PSO). Further investigations using DE, suggest that a SWCNT/LC material is capable of being reconfigured for different binary classification problems, corroborating previous research. In addition, it is able to retain a physical memory of each of the solutions to the problems it has been trained to solve.

[1]  Julian Francis Miller,et al.  Evolution-In-Materio: Solving Machine Learning Classification Problems Using Materials , 2014, PPSN.

[2]  K.W. Wong,et al.  Comparing the performance of different neural networks for binary classification problems , 2009, 2009 Eighth International Symposium on Natural Language Processing.

[3]  Celestine Preetham Lawrence,et al.  Evolution of a designless nanoparticle network into reconfigurable Boolean logic. , 2015, Nature nanotechnology.

[4]  A. Kotsialos,et al.  Evolution of Electronic Circuits using Carbon Nanotube Composites , 2016, Scientific Reports.

[5]  Cengiz S. Ozkan,et al.  Electric Field Assisted Patterning of Neuronal Networks for the Study of Brain Functions , 2003 .

[6]  Nils Blüthgen,et al.  Bacterial computing with engineered populations , 2015, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[7]  Adrian Thompson,et al.  An Evolved Circuit, Intrinsic in Silicon, Entwined with Physics , 1996, ICES.

[8]  Julian Francis Miller,et al.  Function optimization using cartesian genetic programming , 2013, GECCO '13 Companion.

[9]  Jesus A. Gonzalez,et al.  Symbolic One-Class Learning from Imbalanced Datasets: Application in Medical Diagnosis , 2009, Int. J. Artif. Intell. Tools.

[10]  Apostolos Kotsialos,et al.  Manipulating the conductance of single-walled carbon nanotubes based thin films for evolving threshold logic circuits using particle swarm optimisation , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[11]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[12]  C. Krishna Mohan,et al.  Multi-level classification: A generic classification method for medical datasets , 2015, 2015 17th International Conference on E-health Networking, Application & Services (HealthCom).

[13]  Apostolos Kotsialos,et al.  Logic Gate and Circuit Training on Randomly Dispersed Carbon Nanotubes , 2014, Int. J. Unconv. Comput..

[14]  Jon Bird,et al.  Gordon Pask and His Maverick Machines , 2007 .

[15]  P. S. Patheja,et al.  An Enhanced Approach for Weather Forecasting Using Neural Network , 2011, SocProS.

[16]  Apostolos Kotsialos,et al.  Training a Carbon-Nanotube/Liquid Crystal Data Classifier Using Evolutionary Algorithms , 2016, UCNC.

[17]  Julian Francis Miller,et al.  Evolution-in-materio: A frequency classifier using materials , 2014, 2014 IEEE International Conference on Evolvable Systems.

[18]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[19]  Jeff Jones,et al.  Quantitative transformation for implementation of adder circuits in physical systems , 2015, Biosyst..

[20]  Julian Francis Miller,et al.  Evolution-in-materio: Solving bin packing problems using materials , 2014, 2014 IEEE International Conference on Evolvable Systems.

[21]  Michael N. Vrahatis,et al.  Particle swarm optimization for integer programming , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[22]  Apostolos Kotsialos,et al.  Data Classification Using Carbon-Nanotubes and Evolutionary Algorithms , 2016, PPSN.

[23]  A. Kotsialos,et al.  Exploring the alignment of carbon nanotubes dispersed in a liquid crystal matrix using coplanar electrodes , 2015 .

[24]  Paul J. Layzell,et al.  Analysis of unconventional evolved electronics , 1999, CACM.

[25]  M. E. H. Pedersen,et al.  Good Parameters for Differential Evolution , 2010 .

[26]  Apostolos Kotsialos,et al.  Computing with carbon nanotubes: Optimization of threshold logic gates using disordered nanotube/polymer composites , 2015 .

[27]  Susan Stepney,et al.  The neglected pillar of material computation , 2008 .

[28]  Julian Francis Miller,et al.  Evolution in materio: looking beyond the silicon box , 2002, Proceedings 2002 NASA/DoD Conference on Evolvable Hardware.

[29]  Jon Bird,et al.  Gordon Pask His Maverick Machines , 2008 .

[30]  Vicente Alarcón Aquino,et al.  A Biometric System Based on Neural Networks and SVM Using Morphological Feature Extraction from Hand-Shape Images , 2011, Informatica.