Publications

Journal article

Bertone G, Deisenroth MP, Kim JS, Liem S, de Austri RR, Welling Met al., 2019,

Accelerating the BSM interpretation of LHC data with machine learning

, PHYSICS OF THE DARK UNIVERSE, Vol: 24, ISSN: 2212-6864

Journal article

Kuntz J, Thomas P, Stan G-B, Barahona Met al., 2019,

The exit time finite state projection scheme: bounding exit distributions and occupation measures of continuous-time Markov chains

, SIAM Journal on Scientific Computing, Vol: 41, Pages: A748-A769, ISSN: 1064-8275

We introduce the exit time finite state projection (ETFSP) scheme, a truncation- based method that yields approximations to the exit distribution and occupation measure associated with the time of exit from a domain (i.e., the time of first passage to the complement of the domain) of time-homogeneous continuous-time Markov chains. We prove that: (i) the computed approximations bound the measures from below; (ii) the total variation distances between the approximations and the measures decrease monotonically as states are added to the truncation; and (iii) the scheme converges, in the sense that, as the truncation tends to the entire state space, the total variation distances tend to zero. Furthermore, we give a computable bound on the total variation distance between the exit distribution and its approximation, and we delineate the cases in which the bound is sharp. We also revisit the related finite state projection scheme and give a comprehensive account of its theoretical properties. We demonstrate the use of the ETFSP scheme by applying it to two biological examples: the computation of the first passage time associated with the expression of a gene, and the fixation times of competing species subject to demographic noise.

Journal article

Zhong Q, Fan X, Luo X, Toni Fet al., 2019,

An explainable multi-attribute decision model based on argumentation

, Expert Systems with Applications, Vol: 117, Pages: 42-61, ISSN: 0957-4174

We present a multi-attribute decision model and a method for explaining the decisions it recommends based on an argumentative reformulation of the model. Specifically, (i) we define a notion of best (i.e., minimally redundant) decisions amounting to achieving as many goals as possible and exhibiting as few redundant attributes as possible, and (ii) we generate explanations for why a decision is best or better than or as good as another, using a mapping between the given decision model and an argumentation framework, such that best decisions correspond to admissible sets of arguments. Concretely, natural language explanations are generated automatically from dispute trees sanctioning the admissibility of arguments. Throughout, we illustrate the power of our approach within a legal reasoning setting, where best decisions amount to past cases that are most similar to a given new, open case. Finally, we conduct an empirical evaluation of our method with legal practitioners, confirming that our method is effective for the choice of most similar past cases and helpful to understand automatically generated recommendations.

Journal article

Bello G, Dawes T, Duan J, Biffi C, Simoes Monteiro de Marvao A, Howard L, Gibbs S, Wilkins M, Cook S, Rueckert D, O'Regan Det al., 2019,

Deep learning cardiac motion analysis for human survival prediction

, Nature Machine Intelligence, Vol: 1, Pages: 95-104, ISSN: 2522-5839

Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimizing the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be used for prediction tasks. Here we use image sequences of the heart, acquired using cardiac magnetic resonance imaging, to create time-resolved three-dimensional segmentations using a fully convolutional network trained on anatomical shape priors. This dense motion model formed the input to a supervised denoising autoencoder (4Dsurvival), which is a hybrid network consisting of an autoencoder that learns a task-specific latent code representation trained on observed outcome data, yielding a latent representation optimized for survival prediction. To handle right-censored survival outcomes, our network used a Cox partial likelihood loss function. In a study of 302 patients, the predictive accuracy (quantified by Harrell’s C-index) was significantly higher (P = 0.0012) for our model C = 0.75 (95% CI: 0.70–0.79) than the human benchmark of C = 0.59 (95% CI: 0.53–0.65). This work demonstrates how a complex computer vision task using high-dimensional medical image data can efficiently predict human survival.

Journal article

Baroni P, Rago A, Toni F, 2019,

From fine-grained properties to broad principles for gradual argumentation: A principled spectrum

, International Journal of Approximate Reasoning, Vol: 105, Pages: 252-286, ISSN: 0888-613X

The study of properties of gradual evaluation methods in argumentation has received increasing attention in recent years, with studies devoted to various classes of frameworks/ methods leading to conceptually similar but formally distinct properties in different contexts. In this paper we provide a novel systematic analysis for this research landscape by making three main contributions. First, we identify groups of conceptually related properties in the literature, which can be regarded as based on common patterns and, using these patterns, we evidence that many further novel properties can be considered. Then, we provide a simplifying and unifying perspective for these groups of properties by showing that they are all implied by novel parametric principles of (either strict or non-strict) balance and monotonicity. Finally, we show that (instances of) these principles (and thus the group, literature and novel properties that they imply) are satisfied by several quantitative argumentation formalisms in the literature, thus confirming the principles' general validity and utility to support a compact, yet comprehensive, analysis of properties of gradual argumentation.

Journal article

Kormushev P, Ugurlu B, Caldwell DG, Tsagarakis NGet al., 2019,

Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid

, Autonomous Robots, Vol: 43, Pages: 79-95, ISSN: 0929-5593

Modern humanoid robots include not only active compliance but also passive compliance. Apart from improved safety and dependability, availability of passive elements, such as springs, opens up new possibilities for improving the energy efficiency. With this in mind, this paper addresses the challenging open problem of exploiting the passive compliance for the purpose of energy efficient humanoid walking. To this end, we develop a method comprising two parts: an optimization part that finds an optimal vertical center-of-mass trajectory, and a walking pattern generator part that uses this trajectory to produce a dynamically-balanced gait. For the optimization part, we propose a reinforcement learning approach that dynamically evolves the policy parametrization during the learning process. By gradually increasing the representational power of the policy parametrization, it manages to find better policies in a faster and computationally efficient way. For the walking generator part, we develop a variable-center-of-mass-height ZMP-based bipedal walking pattern generator. The method is tested in real-world experiments with the bipedal robot COMAN and achieves a significant 18% reduction in the electric energy consumption by learning to efficiently use the passive compliance of the robot.

Journal article

Altuncu MT, Mayer E, Yaliraki SN, Barahona Met al., 2019,

From free text to clusters of content in health records: An unsupervised graph partitioning approach

, Applied Network Science, Vol: 4, ISSN: 2364-8228

Electronic Healthcare records contain large volumes of unstructured data in different forms. Free text constitutes a large portion of such data, yet this source of richly detailed information often remains under-used in practice because of a lack of suitable methodologies to extract interpretable contentin a timely manner. Here we apply network-theoretical tools to the analysis of free text in Hospital Patient Incident reports in the English National Health Service, to find clusters of reports in an unsupervised manner and at different levels of resolution based directly on the free text descriptions contained within them. To do so, we combine recently developed deep neural network text-embedding methodologies based on paragraph vectors with multi-scale Markov Stability community detection applied to a similarity graph of documents obtained from sparsified text vector similarities. We showcase the approach with the analysis of incident reports submitted in Imperial College Healthcare NHS Trust, London. The multiscale community structure reveals levels of meaning with different resolution in the topics of the dataset, as shown by relevant descriptive terms extracted from thegroups of records, as well as by comparing a posteriori against hand-coded categories assigned by healthcare personnel. Our content communities exhibit good correspondence with well-defined hand-coded categories, yet our results also provide further medical detail in certain areas as well asrevealing complementary descriptors of incidents beyond the external classification. We also discuss how the method can be used to monitor reports over time and across different healthcare providers, and to detect emerging trends that fall outside of pre-existing categories.

Journal article

Eyerich K, Brown S, Perez White B, Tanaka RJ, Bissonette R, Dhar S, Bieber T, Hijnen DJ, Guttman-Yassky E, Irvine A, Thyssen JP, Vestergaard C, Werfel T, Wollenberg A, Paller A, Reynolds NJet al., 2019,

Human and computational models of atopic dermatitis: a review and perspectives by an expert panel of the International Eczema Council

, Journal of Allergy and Clinical Immunology, Vol: 143, Pages: 36-45, ISSN: 0091-6749

Atopic dermatitis (AD) is a prevalent disease worldwide and is associated with systemic comorbidities representing a significant burden on patients, their families, and society. Therapeutic options for AD remain limited, in part because of a lack of well-characterized animal models. There has been increasing interest in developing experimental approaches to study the pathogenesis of human AD in vivo, in vitro, and in silico to better define pathophysiologic mechanisms and identify novel therapeutic targets and biomarkers that predict therapeutic response. This review critically appraises a range of models, including genetic mutations relevant to AD, experimental challenge of human skin in vivo, tissue culture models, integration of “omics” data sets, and development of predictive computational models. Although no one individual model recapitulates the complex AD pathophysiology, our review highlights insights gained into key elements of cutaneous biology, molecular pathways, and therapeutic target identification through each approach. Recent developments in computational analysis, including application of machine learning and a systems approach to data integration and predictive modeling, highlight the applicability of these methods to AD subclassification (endotyping), therapy development, and precision medicine. Such predictive modeling will highlight knowledge gaps, further inform refinement of biological models, and support new experimental and systems approaches to AD.

Conference paper

Kotonya N, Toni F, 2019,

Gradual Argumentation Evaluation for Stance Aggregation in Automated Fake News Detection

, 6th Workshop on Argument Mining (ArgMining), Publisher: ASSOC COMPUTATIONAL LINGUISTICS-ACL, Pages: 156-166

Author Web Link
Cite
Citations: 9

Conference paper

Cyras K, Domínguez J, Karamlou A, Prociuk D, Curcin V, Delaney B, Toni F, Chalkidou K, Darzi Aet al., 2019,

ROAD2H: Learning Decision Support System for Low- and Middle-Income Countries.

, Publisher: AMIA

Journal article

Cocarascu O, Toni F, 2018,

Combining deep learning and argumentative reasoning for the analysis of social media textual content using small datasets

, Computational Linguistics, Vol: 44, Pages: 833-858, ISSN: 0891-2017

The use of social media has become a regular habit for many and has changed the way people interact with each other. In this article, we focus on analysing whether news headlines support tweets and whether reviews are deceptive by analysing the interaction or the influence that these texts have on the others, thus exploiting contextual information. Concretely, we define a deep learning method for Relation-based Argument Mining to extract argumentative relations of attack and support. We then use this method for determining whether news articles support tweets, a useful task in fact-checking settings, where determining agreement towards a statement is a useful step towards determining its truthfulness. Furthermore we use our method for extracting Bipolar Argumentation Frameworks from reviews to help detect whether they are deceptive. We show experimentally that our method performs well in both settings. In particular, in the case of deception detection, our method contributes a novel argumentative feature that, when used in combination with other features in standard supervised classifiers, outperforms the latter even on small datasets.

Journal article

Clarke JM, Warren LR, Arora S, Barahona M, Darzi AWet al., 2018,

Guiding interoperable electronic health records through patient-sharing networks.

, NPJ digital medicine, Vol: 1, Pages: 65-65, ISSN: 2398-6352

Effective sharing of clinical information between care providers is a critical component of a safe, efficient health system. National data-sharing systems may be costly, politically contentious and do not reflect local patterns of care delivery. This study examines hospital attendances in England from 2013 to 2015 to identify instances of patient sharing between hospitals. Of 19.6 million patients receiving care from 155 hospital care providers, 130 million presentations were identified. On 14.7 million occasions (12%), patients attended a different hospital to the one they attended on their previous interaction. A network of hospitals was constructed based on the frequency of patient sharing between hospitals which was partitioned using the Louvain algorithm into ten distinct data-sharing communities, improving the continuity of data sharing in such instances from 0 to 65-95%. Locally implemented data-sharing communities of hospitals may achieve effective accessibility of clinical information without a large-scale national interoperable information system.

Conference paper

Dutordoir V, Salimbeni HR, Hensman J, Deisenroth MPet al., 2018,

Gaussian process conditional density estimation

, Advances in Neural Information Processing Systems, Publisher: Neural Information Processing Systems Conference

Conditional Density Estimation (CDE) models deal with estimating conditional distributions. The conditions imposed on the distribution are the inputs of the model. CDE is a challenging task as there is a fundamental trade-off between model complexity, representational capacity and overfitting. In this work, we propose to extend the model's input with latent variables and use Gaussian processes (GP) to map this augmented input onto samples from the conditional distribution. Our Bayesian approach allows for the modeling of small datasets, but we also provide the machinery for it to be applied to big data using stochastic variational inference. Our approach can be used to model densities even in sparse data regions, and allows for sharing learned structure between conditions. We illustrate the effectiveness and wide-reaching applicability of our model on a variety of real-world problems, such as spatio-temporal density estimation of taxi drop-offs, non-Gaussian noise modeling, and few-shot learning on omniglot images.

Conference paper

Wang K, Shah A, Kormushev P, 2018,

SLIDER: A Bipedal Robot with Knee-less Legs and Vertical Hip Sliding Motion

, 21st International Conference on Climbing and Walking Robots and Support Technologies for Mobile Machines (CLAWAR 2018)

Conference paper

Russo A, Law M, Broda K, 2018,

AAAI 2019, Proceedings pf the 33rd AAAI Conference on Artificial Intelligence

, AAAI-19: Thirty-Third AAAI Conference on Artificial intelligence

Cite

Conference paper

Cyras K, Delaney B, Prociuk D, Toni F, Chapman M, Dominguez J, Curcin Vet al., 2018,

Argumentation for explainable reasoning with conflicting medical recommendations

, Reasoning with Ambiguous and Conflicting Evidence and Recommendations in Medicine (MedRACER 2018), Pages: 14-22

Designing a treatment path for a patient suffering from mul-tiple conditions involves merging and applying multiple clin-ical guidelines and is recognised as a difficult task. This isespecially relevant in the treatment of patients with multiplechronic diseases, such as chronic obstructive pulmonary dis-ease, because of the high risk of any treatment change havingpotentially lethal exacerbations. Clinical guidelines are typi-cally designed to assist a clinician in treating a single condi-tion with no general method for integrating them. Addition-ally, guidelines for different conditions may contain mutuallyconflicting recommendations with certain actions potentiallyleading to adverse effects. Finally, individual patient prefer-ences need to be respected when making decisions.In this work we present a description of an integrated frame-work and a system to execute conflicting clinical guidelinerecommendations by taking into account patient specific in-formation and preferences of various parties. Overall, ourframework combines a patient’s electronic health record datawith clinical guideline representation to obtain personalisedrecommendations, uses computational argumentation tech-niques to resolve conflicts among recommendations while re-specting preferences of various parties involved, if any, andyields conflict-free recommendations that are inspectable andexplainable. The system implementing our framework willallow for continuous learning by taking feedback from thedecision makers and integrating it within its pipeline.

Conference paper

Pardo F, Levdik V, Kormushev P, 2018,

Q-map: A convolutional approach for goal-oriented reinforcement learning.

Goal-oriented learning has become a core concept in reinforcement learning(RL), extending the reward signal as a sole way to define tasks. However, asparameterizing value functions with goals increases the learning complexity,efficiently reusing past experience to update estimates towards several goalsat once becomes desirable but usually requires independent updates per goal.Considering that a significant number of RL environments can support spatialcoordinates as goals, such as on-screen location of the character in ATARI orSNES games, we propose a novel goal-oriented agent called Q-map that utilizesan autoencoder-like neural network to predict the minimum number of stepstowards each coordinate in a single forward pass. This architecture is similarto Horde with parameter sharing and allows the agent to discover correlationsbetween visual patterns and navigation. For example learning how to use aladder in a game could be transferred to other ladders later. We show how thisnetwork can be efficiently trained with a 3D variant of Q-learning to updatethe estimates towards all goals at once. While the Q-map agent could be usedfor a wide range of applications, we propose a novel exploration mechanism inplace of epsilon-greedy that relies on goal selection at a desired distancefollowed by several steps taken towards it, allowing long and coherentexploratory steps in the environment. We demonstrate the accuracy andgeneralization qualities of the Q-map agent on a grid-world environment andthen demonstrate the efficiency of the proposed exploration mechanism on thenotoriously difficult Montezuma's Revenge and Super Mario All-Stars games.

Conference paper

Saputra RP, Kormushev P, 2018,

Casualty detection from 3D point cloud data for autonomous ground mobile rescue robots

, SSRR 2018, Publisher: IEEE

One of the most important features of mobilerescue robots is the ability to autonomously detect casualties,i.e. human bodies, which are usually lying on the ground. Thispaper proposes a novel method for autonomously detectingcasualties lying on the ground using obtained 3D point-clouddata from an on-board sensor, such as an RGB-D camera ora 3D LIDAR, on a mobile rescue robot. In this method, theobtained 3D point-cloud data is projected onto the detectedground plane, i.e. floor, within the point cloud. Then, thisprojected point cloud is converted into a grid-map that isused afterwards as an input for the algorithm to detecthuman body shapes. The proposed method is evaluated byperforming detections of a human dummy, placed in differentrandom positions and orientations, using an on-board RGB-Dcamera on a mobile rescue robot called ResQbot. To evaluatethe robustness of the casualty detection method to differentcamera angles, the orientation of the camera is set to differentangles. The experimental results show that using the point-clouddata from the on-board RGB-D camera, the proposed methodsuccessfully detects the casualty in all tested body positions andorientations relative to the on-board camera, as well as in alltested camera angles.

Conference paper

Wilson J, Hutter F, Deisenroth MP, 2018,

Maximizing acquisition functions for Bayesian optimization

, Advances in Neural Information Processing Systems (NIPS) 2018, ISSN: 1049-5258

Bayesian optimization is a sample-efficient approach to global optimization that relies on theoretically motivated value heuristics (acquisition functions) to guide its search process. Fully maximizing acquisition functions produces the Bayes' decision rule, but this ideal is difficult to achieve since these functions are frequently non-trivial to optimize. This statement is especially true when evaluating queries in parallel, where acquisition functions are routinely non-convex, high-dimensional, and intractable. We first show that acquisition functions estimated via Monte Carlo integration are consistently amenable to gradient-based optimization. Subsequently, we identify a common family of acquisition functions, including EI and UCB, whose characteristics not only facilitate but justify use of greedy approaches for their maximization.

Conference paper

Salimbeni HR, Cheng C-A, Boots B, Deisenroth MPet al., 2018,

Orthogonally decoupled variational Gaussian processes

, Advances in Neural Information Processing Systems (NIPS) 2018, Publisher: Massachusetts Institute of Technology Press, ISSN: 1049-5258

Gaussian processes (GPs) provide a powerful non-parametric framework for rea-soning over functions. Despite appealing theory, its superlinear computational andmemory complexities have presented a long-standing challenge. State-of-the-artsparse variational inference methods trade modeling accuracy against complexity.However, the complexities of these methods still scale superlinearly in the numberof basis functions, implying that that sparse GP methods are able to learn fromlarge datasets only when a small model is used. Recently, a decoupled approachwas proposed that removes the unnecessary coupling between the complexitiesof modeling the mean and the covariance functions of a GP. It achieves a linearcomplexity in the number of mean parameters, so an expressive posterior meanfunction can be modeled. While promising, this approach suffers from optimizationdifficulties due to ill-conditioning and non-convexity. In this work, we propose analternative decoupled parametrization. It adopts an orthogonal basis in the meanfunction to model the residues that cannot be learned by the standard coupled ap-proach. Therefore, our method extends, rather than replaces, the coupled approachto achieve strictly better performance. This construction admits a straightforwardnatural gradient update rule, so the structure of the information manifold that islost during decoupling can be leveraged to speed up learning. Empirically, ouralgorithm demonstrates significantly faster convergence in multiple experiments.

Search or filter publications

Filter by type:

Filter by year:

Results

Search results

Gradual Argumentation Evaluation for Stance Aggregation in Automated Fake News Detection

ROAD2H: Learning Decision Support System for Low- and Middle-Income Countries.

Gaussian process conditional density estimation

SLIDER: A Bipedal Robot with Knee-less Legs and Vertical Hip Sliding Motion

AAAI 2019, Proceedings pf the 33rd AAAI Conference on Artificial Intelligence

Argumentation for explainable reasoning with conflicting medical recommendations

Q-map: A convolutional approach for goal-oriented reinforcement learning.

Maximizing acquisition functions for Bayesian optimization

Orthogonally decoupled variational Gaussian processes

Contact us