We use cookies to ensure that we give you the best experience on our website. By continuing to browse this repository, you give consent for essential cookies to be used. You can read more about our Privacy and Cookie Policy.

Durham Research Online
You are in:

In-Materio Extreme Learning Machines

Jones, Benedict A. H. and Al Moubayed, Noura and Zeze, Dagou A. and Groves, Chris (2022) 'In-Materio Extreme Learning Machines.', in Parallel Problem Solving from Nature – PPSN XVII. , pp. 505-519. Lecture Notes in Computer Science., 13398


Nanomaterial networks have been presented as a building block for unconventional in-Materio processors. Evolution in-Materio (EiM) has previously presented a way to congure and exploit physical materials for computation, but their ability to scale as datasets get larger and more complex remains unclear. Extreme Learning Machines (ELMs) seek to exploit a randomly initialised single layer feed forward neural network by training the output layer only. An analogy for a physical ELM is produced by exploiting nanomaterial networks as material neurons within the hidden layer. Circuit simulations are used to eciently investigate diode-resistor networks which act as our material neurons. These in-Materio ELMs (iM-ELMs) outperform common classication methods and traditional articial ELMs of a similar hidden layer size. For iM-ELMs using the same number of hidden layer neurons, leveraging larger more complex material neuron topologies (with more nodes/electrodes) leads to better performance, showing that these larger materials have a better capability to process data. Finally, iM-ELMs using virtual material neurons, where a single material is re-used as several virtual neurons, were found to achieve comparable results to iM-ELMs which exploited several dierent materials. However, while these Virtual iM-ELMs provide signicant exibility, they sacrice the highly parallelised nature of physically implemented iM-ELMs.

Item Type:Book chapter
Full text:Publisher-imposed embargo until 14 August 2023.
(AM) Accepted Manuscript
File format - PDF
Publisher Web site:
Publisher statement:The final authenticated version is available online at
Date accepted:06 June 2022
Date deposited:03 August 2022
Date of first online publication:14 August 2022
Date first made open access:14 August 2023

Save or Share this output

Look up in GoogleScholar