Evolution-in-materio: evolving computation in materials

Miller, Julian F.; Harding, Simon; Tufte, Gunnar

doi:10.1007/s12065-014-0106-6

Cited by 98 publications

(89 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Contrary to traditional computing with Metal-Oxide-Silicon-Field-Effect-Transistor (MOFSET) technology, where everything is designed, produced and programmed very carefully, EiM uses a bottom up approach where computation is performed by the material without having explicit knowledge of its internal properties [13].…”

Section: Introductionmentioning

confidence: 99%

Data Classification Using Carbon-Nanotubes and Evolutionary Algorithms

Vissol-Gaudin

Kotsialos

Massey

et al. 2016

Parallel Problem Solving From Nature – PPSN XIV

View full text Add to dashboard Cite

The nal publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-45823-660Additional information: Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-pro t purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. Abstract. The potential of Evolution in Materio (EiM) for machine learning problems is explored here. This technique makes use of evolutionary algorithms (EAs) to influence the processing abilities of an unconfigured physically rich medium, via exploitation of its physical properties. The EiM results reported are obtained using particle swarm optimisation (PSO) and differential evolution (DE) to exploit the complex voltage/current relationship of a mixture of single walled carbon nanotubes (SWCNTs) and liquid crystals (LCs). The computational problem considered is simple binary data classification. Results presented are consistent and reproducible. The evolutionary process based on EAs has the capacity to evolve the material to a state where data classification can be performed. Finally, it appears that through the use of smooth signal inputs, PSO produces classifiers out of the SWCNT/LC substrate which generalise better than those evolved with DE.

show abstract

Section: Introductionmentioning

confidence: 99%

Data Classification Using Carbon-Nanotubes and Evolutionary Algorithms

Vissol-Gaudin

Kotsialos

Massey

et al. 2016

Parallel Problem Solving From Nature – PPSN XIV

View full text Add to dashboard Cite

show abstract

“…Physical output signals are read from the material and converted to output data in the computer. A fitness value is obtained from the output data and supplied as a fitness of a genotype to the evolutionary algorithm [11]. Figure 1 shows conceptual overview of EIM.…”

Section: Conceptual Overview Of Evolution-in-materiomentioning

confidence: 99%

“…1. Concept of evolution-in-materio [11] be reconfigurable, i.e., it should be able to be evolved over many configurations to get the desired response. It is also important for a physical material to be able to be "reset" in some way before applying new input signals to it, otherwise it might preserve some memory of a past configuration and give fitness scores that are dependent on the past.…”

Section: Conceptual Overview Of Evolution-in-materiomentioning

confidence: 99%

Evolution-In-Materio: Solving Machine Learning Classification Problems Using Materials

Mohid

Miller

Harding

et al. 2014

Parallel Problem Solving From Nature – PPSN XIII

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Evolution in Materio (EIM) [4,5,6] is such an unconventional approach where the underlying physical properties of bulk materials are explored and exploited for computation. In contrast to a traditional approach where a substrate, e.g.…”

Section: Introductionmentioning

confidence: 99%

“…An intrinsic approach to EIM allowing the physical artefact to be assessed in-situ is preferred to get access to all inherent physical properties of the material [6]. Intrinsic evolution requires an interface that can bridge the gap between the analogue physical world of materials and the digital world of EAs.…”

Section: Introductionmentioning

confidence: 99%

Mecobo: A Hardware and Software Platform for In Materio Evolution

Lykkebø

Harding

Tufte

et al. 2014

Unconventional Computation and Natural Computation

Self Cite

View full text Add to dashboard Cite

Abstract. Evolution in Materio (EIM) exploits properties of physical systems to compute. "Designs" are evolved instead of a traditional top down design approach. Computation is a product of the state(s) of the material and input data. Evolution manipulates physical processes by stimulating materials assessed in situ. A hardware software platform designed for EIM experimentation is presented. The platform with features especially for EIM is described together with demonstration experiments using carbon nanotubes in a thick film placed on micro electrode arrays.

show abstract

Evolution-in-materio: evolving computation in materials

Cited by 98 publications

References 64 publications

Data Classification Using Carbon-Nanotubes and Evolutionary Algorithms

Data Classification Using Carbon-Nanotubes and Evolutionary Algorithms

Evolution-In-Materio: Solving Machine Learning Classification Problems Using Materials

Mecobo: A Hardware and Software Platform for In Materio Evolution

Contact Info

Product

Resources

About