Computing Based on Material Training: Application to Binary Classification Problems

Evolution-in-materio is a form of unconventional computing combining materials' training and evolutionary search algorithms. In previous work, a mixture of single-walled-carbon-nanotubes (SWCNTs) dispersed in a liquid crystal (LC) was trained so that its morphology and electrical properties were gradually changed to perform a computational task. Material-based computation is treated as an optimisation problem with a hybrid search space consisting of the voltages used for creating the electrical field and the material's infinitely possible SWCNT arrangements in LC. In this paper, we study solutions using synthetic data with a non-linear separating boundary. In addition, results for two real life datasets with partly merged classes are presented. The training process is based on a differential evolution (DE) algorithm, which subjects the SWCNT/LC material to repeated electrical charging, leading to progressive morphological and electric conductivity modifications. It is shown that the material configuration the DE algorithm converges to form a non-negligible part of the solution. Furthermore, the problem's complexity is relevant to the properties of the resulting "physical solver". The material structures created when training for a problem allow the retraining for a less complex one. The result is a doubly-trained material that keeps the memory of the original more complex problem. This is not the case for doubly-trained materials where initial training is for the less complex problem. The optimal electric field found by the DE algorithm is also a necessary solution component for the material's output to be interpreted as a computation.

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

[2]  Julian Francis Miller,et al.  Evolution In Materio: Evolving Logic Gates in Liquid Crystal , 2007, Int. J. Unconv. Comput..

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

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

[5]  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).

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

[7]  Apostolos Kotsialos,et al.  Solving binary classification problems with carbon nanotube / liquid crystal composites and evolutionary algorithms , 2017, 2017 IEEE Congress on Evolutionary Computation (CEC).

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

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

[10]  J. Elmore,et al.  Variability in interpretive performance at screening mammography and radiologists' characteristics associated with accuracy. , 2009, Radiology.

[11]  Juan Humberto Sossa Azuela,et al.  Dendrite Morphological Neural Networks trained by Differential Evolution , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

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

[13]  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.

[14]  Julian Francis Miller,et al.  Evolution in materio: a tone discriminator in liquid crystal , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[15]  J. Heidelbaugh,et al.  Cirrhosis and chronic liver failure: part I. Diagnosis and evaluation. , 2006, American family physician.

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

[17]  Julian Francis Miller,et al.  Evolution In Materio: Investigating the Stability of Robot Controllers Evolved in Liquid Crystal , 2005, ICES.

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

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

[20]  Tin Kam Ho,et al.  Complexity Measures of Supervised Classification Problems , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Julian Francis Miller,et al.  Evolution-in-materio: evolving computation in materials , 2014, Evolutionary Intelligence.