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.
1 code implementation • 3 Mar 2023 • Matthew O. A. Ellis, Alex Welbourne, Stephan J. Kyle, Paul W. Fry, Dan A. Allwood, Thomas J. Hayward, Eleni Vasilaki
For single measurements, the rule results in binary synapses with minimal stochasticity, sacrificing potential performance for robustness.
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.
1 code implementation • 11 Oct 2021 • Anil Ozdemir, Mark Scerri, Andrew B. Barron, Andrew Philippides, Michael Mangan, Eleni Vasilaki, Luca Manneschi
We report that the addition of ESNs to pre-processed convolutional neural networks led to a dramatic boost in performance in comparison to non-recurrent networks in five out of six standard benchmarks (GardensPoint, SPEDTest, ESSEX3IN1, Oxford RobotCar, and Nordland), demonstrating that ESNs are able to capture the temporal structure inherent in VPR problems.
no code implementations • 23 Feb 2021 • Matthew T. Whelan, Tony J. Prescott, Eleni Vasilaki
Hippocampal reverse replay is thought to contribute to learning, and particularly reinforcement learning, in animals.
no code implementations • 11 Jan 2021 • Luca Manneschi, Matthew O. A. Ellis, Guido Gigante, Andrew C. Lin, Paolo del Giudice, Eleni Vasilaki
Echo state networks (ESNs) are a powerful form of reservoir computing that only require training of linear output weights whilst the internal reservoir is formed of fixed randomly connected neurons.
no code implementations • 30 Apr 2020 • Adnan Mehonic, Abu Sebastian, Bipin Rajendran, Osvaldo Simeone, Eleni Vasilaki, Anthony J. Kenyon
Machine learning, particularly in the form of deep learning, has driven most of the recent fundamental developments in artificial intelligence.
1 code implementation • 16 Mar 2020 • Avgoustinos Vouros, Eleni Vasilaki
We consider the problem of data clustering with unidentified feature quality and when a small amount of labelled data is provided.
no code implementations • 4 Dec 2019 • Luca Manneschi, Andrew C. Lin, Eleni Vasilaki
The read-out weights and the thresholds are learned by an on-line gradient rule that minimises an error function on the outputs of the network.
2 code implementations • 26 Aug 2019 • Avgoustinos Vouros, Stephen Langdell, Mike Croucher, Eleni Vasilaki
K-Means is one of the most used algorithms for data clustering and the usual clustering method for benchmarking.
no code implementations • 19 Jul 2019 • Luca Manneschi, Andrew C. Lin, Eleni Vasilaki
In this work we took inspiration from the fruit fly brain to formulate a novel machine learning algorithm that is able to optimize the sparsity level of a reservoir by changing the firing thresholds of the nodes.
1 code implementation • 20 Nov 2017 • Avgoustinos Vouros, Tiago V. Gehring, Kinga Szydlowska, Artur Janusz, Mike Croucher, Katarzyna Lukasiuk, Witold Konopka, Carmen Sandi, Zehai Tu, Eleni Vasilaki
The Morris Water Maze is commonly used in behavioural neuroscience for the study of spatial learning with rodents.
no code implementations • 12 Oct 2017 • Eleni Vasilaki
The Epicurean Philosophy is commonly thought as simplistic and hedonistic.
no code implementations • 20 Sep 2016 • Alvin Pastore, Umberto Esposito, Eleni Vasilaki
Decision making in uncertain and risky environments is a prominent area of research.