The University of Southampton
Warning! Your browser is out-of-date and not compatible with this website. Please download a new secure and faster browser to view this website correctly.

Nanoelectronics collaboration draws international acclaim for advances in intelligent autonomous systems

Published: 
26 January 2017
Illustration

Transdisciplinary research, driven by expertise from Electronics and Computer Science (ECS) at the University of Southampton, has attracted global recognition for speeding the creation of intelligent autonomous systems.

The collaboration, which has successfully demonstrated unsupervised learning tasks that could be applied to powerful future devices, has been highlighted this winter in the international Nature Nanotechnology journal.

Researchers from Southampton’s Nanoelectronics and Nanotechnology research group have created a network of nanoscale devices – known as a memristors – that use unmanned machine learning protocols to observe and recognise letters of the alphabet, emulating the autonomous synoptic functions of the human brain.

The analog memristors, which have been developed with support of the EU-funded Real neurons-nanoelectronics Architecture with Memristive Plasticity (RAMP) project, have also been verified with noisy or incomplete input images.

Dr Themis Prodromakis, a Reader in Nanoelectronics at ECS and an Engineering and Physical Sciences Research Council (EPSRC) Fellow, said: “It is extremely satisfying to see the outcomes of our collaborative research programme highlighted in such a prestigious journal. The unsupervised learning demonstrated through the memristors’ image processing will have significant applications in future embedded systems used in the areas of big data and the Internet of Things.”

The recent Nature Nanotechnology journal highlight draws upon an article published in Frontiers of Neuroscience, entitled Analog Memristive Synapse in Spiking Networks Implementing Unsupervised Learning. The paper proposes a new analog memristor capable of pattern recognition after an unsupervised training process. These learning abilities would enable a new wave systems capable of performing tasks that would be difficult for conventional computing systems.

Share this article FacebookGoogle+TwitterWeibo

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×