no code implementations • 16 Jan 2024 • David Ireland, Giovanni Montana
We further dissect the factors influencing REValueD's performance, evaluating the significance of the regularisation loss and the scalability of REValueD with increasing sub-actions per dimension.
no code implementations • 30 Oct 2023 • Mianchu Wang, Rui Yang, Xi Chen, Hao Sun, Giovanni Montana, Meng Fang
In this work, we propose Goal-conditioned Offline Planning (GOPlan), a novel model-based framework that contains two key phases: (1) pretraining a prior policy capable of capturing multi-modal action distribution within the multi-goal dataset; (2) employing the reanalysis method with planning to generate imagined trajectories for funetuning policies.
1 code implementation • 8 Apr 2023 • George Watkins, Giovanni Montana, Juergen Branke
The graph colouring problem consists of assigning labels, or colours, to the vertices of a graph such that no two adjacent vertices share the same colour.
1 code implementation • 26 Mar 2023 • Alex Beeson, Giovanni Montana
Offline reinforcement learning agents seek optimal policies from fixed data sets.
no code implementations • 16 Mar 2023 • Mianchu Wang, Yue Jin, Giovanni Montana
Offline reinforcement learning (RL) aims to infer sequential decision policies using only offline datasets.
no code implementations • 8 Dec 2022 • Charles A. Hepburn, Giovanni Montana
Furthermore, using the D4RL benchmarking suite, we demonstrate that state-of-the-art results are obtained by combining TS with two existing offline learning methodologies reliant on BC, model-based offline planning (MBOP) and policy constraint (TD3+BC).
no code implementations • 21 Nov 2022 • Alex Beeson, Giovanni Montana
The ability to discover optimal behaviour from fixed data sets has the potential to transfer the successes of reinforcement learning (RL) to domains where data collection is acutely problematic.
no code implementations • 21 Nov 2022 • Charles A. Hepburn, Giovanni Montana
We propose a model-based data augmentation strategy, Trajectory Stitching (TS), to improve the quality of sub-optimal historical trajectories.
no code implementations • 4 Jul 2022 • Matthew MacPherson, Keerthini Muthuswamy, Ashik Amlani, Charles Hutchinson, Vicky Goh, Giovanni Montana
Understanding the internal physiological changes accompanying the aging process is an important aspect of medical image interpretation, with the expected changes acting as a baseline when reporting abnormal findings.
1 code implementation • 20 May 2022 • David Ireland, Giovanni Montana
To solve CO problems, LeNSE is provided with a discriminative embedding trained using any existing heuristics using only on a small portion of the original graph.
1 code implementation • 27 Jul 2021 • Nick Byrne, James R Clough, Isra Valverde, Giovanni Montana, Andrew P King
Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration.
no code implementations • 22 May 2021 • Aydan Gasimova, Giovanni Montana, Daniel Rueckert
Gathering manually annotated images for the purpose of training a predictive model is far more challenging in the medical domain than for natural images as it requires the expertise of qualified radiologists.
2 code implementations • 9 Sep 2020 • Henry Charlesworth, Giovanni Montana
Training agents to autonomously learn how to use anthropomorphic robotic hands has the potential to lead to systems capable of performing a multitude of complex manipulation tasks in unstructured and uncertain environments.
no code implementations • 21 Aug 2020 • Nick Byrne, James R. Clough, Giovanni Montana, Andrew P. King
With respect to spatial overlap, CNN-based segmentation of short axis cardiovascular magnetic resonance (CMR) images has achieved a level of performance consistent with inter observer variation.
no code implementations • 5 Aug 2020 • Ozsel Kilinc, Giovanni Montana
Learning robot manipulation through deep reinforcement learning in environments with sparse rewards is a challenging task.
1 code implementation • NeurIPS 2020 • Henry Charlesworth, Giovanni Montana
Learning with sparse rewards remains a significant challenge in reinforcement learning (RL), especially when the aim is to train a policy capable of achieving multiple different goals.
no code implementations • 17 Feb 2020 • Saad Mohamad, Giovanni Montana
Existing sampling strategies for experience replay like uniform sampling or prioritised experience replay do not explicitly try to control the variance of the gradient estimates.
no code implementations • 12 Feb 2020 • Emanuele Pesce, Giovanni Montana
In artificial multi-agent systems, the ability to learn collaborative policies is predicated upon the agents' communication skills: they must be able to encode the information received from the environment and learn how to share it with other agents as required by the task at hand.
2 code implementations • 16 Oct 2019 • Ozsel Kilinc, Giovanni Montana
In order to exploit this idea, we introduce a framework whereby an object locomotion policy is initially obtained using a realistic physics simulator.
no code implementations • 23 Aug 2019 • Nick Byrne, James R. Clough, Isra Valverde, Giovanni Montana, Andrew P. King
In a series of five-fold cross-validations, we demonstrate the performance gain produced by this pipeline and the relevance of topological considerations to the segmentation of congenital heart defects.
no code implementations • 14 Aug 2019 • Yang Hu, Giovanni Montana
We demonstrate its performance compared to a state-of-the-art approach and several ablation cases, visualize and interpret the hidden factors, and identify avenues for future improvements.
no code implementations • 29 Jan 2019 • Zhana Kuncheva, Giovanni Montana
When dealing with real life data, communities at one or more scales can go undiscovered if appropriate parameter ranges are not selected.
1 code implementation • 12 Jan 2019 • Emanuele Pesce, Giovanni Montana
In this work, we propose a framework for multi-agent training using deep deterministic policy gradients that enables concurrent, end-to-end learning of an explicit communication protocol through a memory device.
no code implementations • 3 Dec 2018 • Ozsel Kilinc, Giovanni Montana
An agent's policy depends on its own private observations as well as those explicitly shared by others through a communication medium.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 27 Sep 2018 • Nicoló Savioli, Miguel Silva Vieira, Pablo Lamata, Giovanni Montana
The clinical management of several cardiovascular conditions, such as pulmonary hypertension, require the assessment of the right ventricular (RV) function.
no code implementations • 31 Aug 2018 • Nicoló Savioli, Miguel Silva Vieira, Pablo Lamata, Giovanni Montana
Our initial experiments suggest that significant improvement in performance can potentially be achieved by using a recurrent neural network component that explicitly learns cardiac motion patterns whilst performing LV segmentation.
no code implementations • 6 Aug 2018 • Nicoló Savioli, Giovanni Montana, Pablo Lamata
Atrial Fibrillation (AF) is a common electro-physiological cardiac disorder that causes changes in the anatomy of the atria.
1 code implementation • 16 Jul 2018 • Ruggiero Santeramo, Samuel Withey, Giovanni Montana
Convolutional neural networks (CNNs) have been successfully employed in recent years for the detection of radiological abnormalities in medical images such as plain x-rays.
no code implementations • 11 Jul 2018 • Nicolo' Savioli, Silvia Visentin, Erich Cosmi, Enrico Grisan, Pablo Lamata, Giovanni Montana
The automatic analysis of ultrasound sequences can substantially improve the efficiency of clinical diagnosis.
no code implementations • 11 Dec 2017 • Mauro Annarumma, Giovanni Montana
Many radiological studies can reveal the presence of several co-existing abnormalities, each one represented by a distinct visual pattern.
no code implementations • 4 Dec 2017 • Emanuele Pesce, Petros-Pavlos Ypsilantis, Samuel Withey, Robert Bakewell, Vicky Goh, Giovanni Montana
We propose two network architectures for the classification of images likely to contain pulmonary nodules using both weak labels and manually-delineated bounding boxes, when these are available.
no code implementations • 29 Jan 2017 • Dimosthenis Tsagkrasoulis, Giovanni Montana
An increasing array of biomedical and computer vision applications requires the predictive modeling of complex data, for example images and shapes.
no code implementations • 23 Jan 2017 • Petros-Pavlos Ypsilantis, Giovanni Montana
X-rays are commonly performed imaging tests that use small amounts of radiation to produce pictures of the organs, tissues, and bones of the body.
1 code implementation • 8 Dec 2016 • James H. Cole, Rudra PK Poudel, Dimosthenis Tsagkrasoulis, Matthan WA Caan, Claire Steves, Tim D Spector, Giovanni Montana
Here we sought to further establish the credentials of "brain-predicted age" as a biomarker of individual differences in the brain ageing process, using a predictive modelling approach based on deep learning, and specifically convolutional neural networks (CNN), and applied to both pre-processed and raw T1-weighted MRI data.
no code implementations • 28 Oct 2016 • Ricardo Pio Monti, Christoforos Anagnostopoulos, Giovanni Montana
In this work consider the problem of learning $\ell_1$ regularized linear models in the context of streaming data.
no code implementations • 28 Sep 2016 • Petros-Pavlos Ypsilantis, Giovanni Montana
In this article we propose a deep artificial neural network architecture, ReCTnet, for the fully-automated detection of pulmonary nodules in CT scans.
no code implementations • WS 2016 • Savelie Cornegruta, Robert Bakewell, Samuel Withey, Giovanni Montana
Motivated by the need to automate medical information extraction from free-text radiological reports, we present a bi-directional long short-term memory (BiLSTM) neural network architecture for modelling radiological language.
Medical Named Entity Recognition named-entity-recognition +5
no code implementations • 13 Aug 2016 • Rudra P. K. Poudel, Pablo Lamata, Giovanni Montana
In cardiac magnetic resonance imaging, fully-automatic segmentation of the heart enables precise structural and functional measurements to be taken, e. g. from short-axis MR images of the left-ventricle.
no code implementations • 9 May 2016 • Zi Wang, Vyacheslav Karolis, Chiara Nosarti, Giovanni Montana
These latent factors can be used to produce low-dimensional visualisations of the data that emphasise age-specific effects once the shared effects have been accounted for.
no code implementations • 1 May 2016 • Ricardo Pio Monti, Romy Lorenz, Robert Leech, Christoforos Anagnostopoulos, Giovanni Montana
Large-scale automated meta-analysis of neuroimaging data has recently established itself as an important tool in advancing our understanding of human brain function.
no code implementations • 7 Dec 2015 • Ricardo Pio Monti, Christoforos Anagnostopoulos, Giovanni Montana
In neuroimaging data analysis, Gaussian graphical models are often used to model statistical dependencies across spatially remote brain regions known as functional connectivity.
no code implementations • 24 Nov 2015 • Romy Lorenz, Ricardo P Monti, Ines R Violante, Aldo A. Faisal, Christoforos Anagnostopoulos, Robert Leech, Giovanni Montana
Bayesian optimization has been proposed as a practical and efficient tool through which to tune parameters in many difficult settings.
no code implementations • 6 Nov 2015 • Ricardo Pio Monti, Romy Lorenz, Robert Leech, Christoforos Anagnostopoulos, Giovanni Montana
We propose a framework to perform streaming covariance selection.
no code implementations • 6 Jul 2015 • Zhana Kuncheva, Giovanni Montana
In this article we propose a community detection algorithm, LART (Locally Adaptive Random Transitions), for the detection of communities that are shared by either some or all the layers in the multiplex.
no code implementations • 4 Mar 2015 • Zi Wang, Wei Yuan, Giovanni Montana
The proposed methodology can be interpreted as an extension of principal component analysis in that it provides the means to decompose the total sample variance in each tissue into the sum of two components: one capturing the variance that is shared across tissues, and one isolating the tissue-specific variances.
2 code implementations • 9 Feb 2015 • Alexandre de Brebisson, Giovanni Montana
To our knowledge, our technique is the first to tackle the anatomical segmentation of the whole brain using deep neural networks.
no code implementations • 9 Feb 2015 • Adrien Payan, Giovanni Montana
Pattern recognition methods using neuroimaging data for the diagnosis of Alzheimer's disease have been the subject of extensive research in recent years.
no code implementations • 8 Feb 2015 • Ricardo Pio Monti, Romy Lorenz, Christoforos Anagnostopoulos, Robert Leech, Giovanni Montana
Such studies have recently gained momentum and have been applied in a wide variety of settings; ranging from training of healthy subjects to self-regulate neuronal activity to being suggested as potential treatments for clinical populations.
no code implementations • 14 Oct 2013 • Ricardo Pio Monti, Peter Hellyer, David Sharp, Robert Leech, Christoforos Anagnostopoulos, Giovanni Montana
We apply the SINGLE algorithm to functional MRI data from 24 healthy patients performing a choice-response task to demonstrate the dynamic changes in network structure that accompany a simple but attentionally demanding cognitive task.
no code implementations • 24 Sep 2013 • Aaron Sim, Dimosthenis Tsagkrasoulis, Giovanni Montana
We propose a non-parametric regression methodology, Random Forests on Distance Matrices (RFDM), for detecting genetic variants associated to quantitative phenotypes representing the human brain's structure or function, and obtained using neuroimaging techniques.