no code implementations • 10 Apr 2024 • Xiaoxi Wei, Jyotindra Narayan, A. Aldo Faisal
It outperforms conventional deep learning methods, showcasing the potential for effective use of larger, heterogeneous data sets with enhanced privacy as a model-agnostic meta-framework.
no code implementations • 29 Feb 2024 • Lauren Stumpf, Balasundaram Kadirvelu, Sigourney Waibel, A. Aldo Faisal
We develop a transformer framework, called Speaker-Agnostic Latent Regularisation (SALR), incorporating a multi-task learning objective and contrastive learning for speaker-independent multi-class dysarthria severity classification.
no code implementations • 21 Nov 2023 • Siyi Li, Arnaud Robert, A. Aldo Faisal, Matthew D. Piggott
This work proposes a novel data-driven model capable of providing accurate predictions for the power generation of all wind turbines in wind farms of arbitrary layout, yaw angle configurations and wind conditions.
no code implementations • 11 Sep 2023 • Nat Wannawas, A. Aldo Faisal
Reinforcement learning of real-world tasks is very data inefficient, and extensive simulation-based modelling has become the dominant approach for training systems.
no code implementations • 20 Jun 2023 • Jinpei Han, Xiaoxi Wei, A. Aldo Faisal
This indicates that the GNN-based transfer learning framework can effectively aggregate knowledge from multiple datasets with different electrode layouts, leading to improved generalization in subject-independent MI EEG classification.
no code implementations • 17 Mar 2023 • Nat Wannawas, A. Aldo Faisal
By using just 100 seconds of cycling data, our method can deliver a fine-tuned pattern that gives better cycling performance.
no code implementations • 10 Jan 2023 • Nat Wannawas, A. Aldo Faisal
In combination, our customisable models and RL-based control method open the possibility of delivering customised FES controls for different subjects and settings with minimal engineering intervention.
no code implementations • 10 Jan 2023 • Nat Wannawas, A. Aldo Faisal
Yet, one remaining challenge of using RL to control FES is unobservable muscle fatigue that progressively changes as an unknown function of the stimulation, breaking the Markovian assumption of RL.
no code implementations • 20 Nov 2022 • Xiaoxi Wei, A. Aldo Faisal
Here, we demonstrate a federated deep transfer learning technique, the Multi-dataset Federated Separate-Common-Separate Network (MF-SCSN) based on our previous work of SCSN, which integrates privacy-preserving properties into deep transfer learning to utilise data sets with different tasks.
no code implementations • 16 Sep 2022 • Nat Wannawas, Ali Shafti, A. Aldo Faisal
Functional Electrical Stimulation (FES) is a technique to evoke muscle contraction through low-energy electrical signals.
no code implementations • 2 Mar 2022 • Yiming Liu, Raz Leib, William Dudley, Ali Shafti, A. Aldo Faisal, David W. Franklin
The task requires that the two sides coordinate with each other, in real-time, to balance the ball at the target.
no code implementations • 16 Feb 2022 • Ali Shafti, Victoria Derks, Hannah Kay, A. Aldo Faisal
Explainability, interpretability and how much they affect human trust in AI systems are ultimately problems of human cognition as much as machine learning, yet the effectiveness of AI recommendations and the trust afforded by end-users are typically not evaluated quantitatively.
1 code implementation • 14 Feb 2022 • Xiaoxi Wei, A. Aldo Faisal, Moritz Grosse-Wentrup, Alexandre Gramfort, Sylvain Chevallier, Vinay Jayaram, Camille Jeunet, Stylianos Bakas, Siegfried Ludwig, Konstantinos Barmpas, Mehdi Bahri, Yannis Panagakis, Nikolaos Laskaris, Dimitrios A. Adamos, Stefanos Zafeiriou, William C. Duong, Stephen M. Gordon, Vernon J. Lawhern, Maciej Śliwowski, Vincent Rouanne, Piotr Tempczyk
Task 2 is centred on Brain-Computer Interfacing (BCI), addressing motor imagery decoding across both subjects and data sets.
no code implementations • 22 Jan 2022 • Paul Festor, Ali Shafti, Alex Harston, Michey Li, Pavel Orlov, A. Aldo Faisal
Our evaluation shows that intention prediction is not a naive result of the data, but rather relies on non-linear temporal processing of gaze cues.
no code implementations • 16 Sep 2021 • Paul Festor, Giulia Luise, Matthieu Komorowski, A. Aldo Faisal
Reinforcement Learning (RL) is emerging as tool for tackling complex control and decision-making problems.
no code implementations • 20 Mar 2021 • Luchen Li, A. Aldo Faisal
Distributional Reinforcement Learning (RL) maintains the entire probability distribution of the reward-to-go, i. e. the return, providing more learning signals that account for the uncertainty associated with policy performance, which may be beneficial for trading off exploration and exploitation and policy learning in general.
no code implementations • 9 Mar 2021 • Xiaoxi Wei, Pablo Ortega, A. Aldo Faisal
We propose a multi-branch deep transfer network, the Separate-Common-Separate Network (SCSN) based on splitting the network's feature extractors for individual subjects.
no code implementations • 9 Mar 2021 • Nat Wannawas, Ali Shafti, A. Aldo Faisal
However, an open challenge remains on how to restore motor abilities to human limbs through FES, as the problem of controlling the stimulation is unclear.
no code implementations • 4 Mar 2021 • Nat Wannawas, Mahendran Subramanian, A. Aldo Faisal
Functional Electrical Stimulation (FES) can restore motion to a paralysed person's muscles.
no code implementations • 4 Mar 2021 • Mahendran Subramanian, Suhyung Park, Pavel Orlov, Ali Shafti, A. Aldo Faisal
We have pioneered the Where-You-Look-Is Where-You-Go approach to controlling mobility platforms by decoding how the user looks at the environment to understand where they want to navigate their mobility device.
no code implementations • 25 Feb 2021 • Ali Shafti, A. Aldo Faisal
We combine wearable eye tracking, the visual context of the environment and the structural grammar of human actions to create a cognitive-level assistive robotic setup that enables the users in fulfilling activities of daily living, while conserving interpretability, and the agency of the user.
no code implementations • 2 Mar 2020 • Ali Shafti, Jonas Tjomsland, William Dudley, A. Aldo Faisal
We then use this setup to perform systematic experiments on human/agent behaviour and adaptation when co-learning a policy for the collaborative game.
no code implementations • 2 Dec 2019 • Jonas Tjomsland, Ali Shafti, A. Aldo Faisal
We present a robotic setup for real-world testing and evaluation of human-robot and human-human collaborative learning.
no code implementations • 7 Oct 2019 • Petros Christodoulou, Robert Tjarko Lange, Ali Shafti, A. Aldo Faisal
From a young age humans learn to use grammatical principles to hierarchically combine words into sentences.
no code implementations • 11 Sep 2019 • Alexander Makrigiorgos, Ali Shafti, Alex Harston, Julien Gerard, A. Aldo Faisal
Autonomous driving is a multi-task problem requiring a deep understanding of the visual environment.
no code implementations • 14 Apr 2019 • Benjamin Beyret, Ali Shafti, A. Aldo Faisal
This is currently a challenge in deep learning systems.
no code implementations • 6 Mar 2019 • Matthieu Komorowski, Leo A. Celi, Omar Badawi, Anthony C. Gordon, A. Aldo Faisal
In this document, we explore in more detail our published work (Komorowski, Celi, Badawi, Gordon, & Faisal, 2018) for the benefit of the AI in Healthcare research community.
no code implementations • 27 Jul 2018 • Mickey Li, Noyan Songur, Pavel Orlov, Stefan Leutenegger, A. Aldo Faisal
Incorporating the physical environment is essential for a complete understanding of human behavior in unconstrained every-day tasks.
no code implementations • 22 Jul 2018 • Mireia Ruiz Maymo, Ali Shafti, A. Aldo Faisal
Here we are demonstrating the off-loading of low-level control of assistive robotics and active orthotics, through automatic end-effector orientation control for grasping.
no code implementations • 14 Mar 2018 • Thomas Teh, Chaiyawan Auepanwiriyakul, John Alexander Harston, A. Aldo Faisal
Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot of success in the domain of image-based data, where the data offers a clearly structured topology in the regular lattice of pixels.