no code implementations • 14 Jan 2024 • Luca Manneschi, Ian T. Vidamour, Kilian D. Stenning, Jack C. Gartside, Charles Swindells, Guru Venkat, David Griffin, Susan Stepney, Will R. Branford, Thomas Hayward, Matt O Ellis, Eleni Vasilaki
Physically implemented neural networks hold the potential to achieve the performance of deep learning models by exploiting the innate physical properties of devices as computational tools.
no code implementations • 9 Dec 2022 • Dan A Allwood, Matthew O A Ellis, David Griffin, Thomas J Hayward, Luca Manneschi, Mohammad F KH Musameh, Simon O'Keefe, Susan Stepney, Charles Swindells, Martin A Trefzer, Eleni Vasilaki, Guru Venkat, Ian Vidamour, Chester Wringe
Neural networks have revolutionized the area of artificial intelligence and introduced transformative applications to almost every scientific field and industry.
no code implementations • 29 Nov 2021 • Ian T Vidamour, Matthew O A Ellis, David Griffin, Guru Venkat, Charles Swindells, Richard W S Dawidek, Thomas J Broomhall, Nina-Juliane Steinke, Joshaniel F K Cooper, Francisco Maccherozzi, Sarnjeet S Dhesi, Susan Stepney, Eleni Vasilaki, Dan A Allwood, Thomas J Hayward
Devices based on arrays of interconnected magnetic nano-rings with emergent magnetization dynamics have recently been proposed for use in reservoir computing applications, but for them to be computationally useful it must be possible to optimise their dynamical responses.