Committee machines-a universal method to deal with non-idealities in memristor-based neural networks.

TLDR: A technology-agnostic approach, committee machines, is demonstrated, which increases the inference accuracy of memristive neural networks that suffer from device variability, faulty devices, random telegraph noise and line resistance.

Abstract: Artificial neural networks are notoriously power- and time-consuming when implemented on conventional von Neumann computing systems. Consequently, recent years have seen an emergence of research in machine learning hardware that strives to bring memory and computing closer together. A popular approach is to realise artificial neural networks in hardware by implementing their synaptic weights using memristive devices. However, various device- and system-level non-idealities usually prevent these physical implementations from achieving high inference accuracy. We suggest applying a well-known concept in computer science—committee machines—in the context of memristor-based neural networks. Using simulations and experimental data from three different types of memristive devices, we show that committee machines employing ensemble averaging can successfully increase inference accuracy in physically implemented neural networks that suffer from faulty devices, device-to-device variability, random telegraph noise and line resistance. Importantly, we demonstrate that the accuracy can be improved even without increasing the total number of memristors. Designing reliable and energy-efficient memristor-based artificial neural networks remains a challenge. Here, the authors demonstrate a technology-agnostic approach, committee machines, which increases the inference accuracy of memristive neural networks that suffer from device variability, faulty devices, random telegraph noise and line resistance.