Search or filter publications

Filter by type:

Filter by publication type

Filter by year:

to

Results

  • Showing results for:
  • Reset all filters

Search results

  • CONFERENCE PAPER
    Baroni P, Rago A, Toni F, 2018,

    How Many Properties Do We Need for Gradual Argumentation?

    , Publisher: AAAI Press, Pages: 1736-1743
  • JOURNAL ARTICLE
    Biffi C, de Marvao A, Attard MI, Dawes TJW, Whiffin N, Bai W, Shi W, Francis C, Meyer H, Buchan R, Cook SA, Rueckert D, O'Regan DPet al., 2018,

    Three-dimensional cardiovascular imaging-genetics: a mass univariate framework

    , BIOINFORMATICS, Vol: 34, Pages: 97-103, ISSN: 1367-4803
  • JOURNAL ARTICLE
    Chamberlain B, Levy-Kramer J, Humby C, Deisenroth MPet al., 2018,

    Real-time community detection in full social networks on a laptop

    , PLoS ONE, Vol: 13, ISSN: 1932-6203

    For a broad range of research and practical applications it is important to understand the allegiances, communities and structure of key players in society. One promising direction towards extracting this information is to exploit the rich relational data in digital social networks (the social graph). As global social networks (e.g., Facebook and Twitter) are very large, most approaches make use of distributed computing systems for this purpose. Distributing graph processing requires solving many difficult engineering problems, which has lead some researchers to look at single-machine solutions that are faster and easier to maintain. In this article, we present an approach for analyzing full social networks on a standard laptop, allowing for interactive exploration of the communities in the locality of a set of user specified query vertices. The key idea is that the aggregate actions of large numbers of users can be compressed into a data structure that encapsulates the edge weights between vertices in a derived graph. Local communities can be constructed by selecting vertices that are connected to the query vertices with high edge weights in the derived graph. This compression is robust to noise and allows for interactive queries of local communities in real-time, which we define to be less than the average human reaction time of 0.25s. We achieve single-machine real-time performance by compressing the neighborhood of each vertex using minhash signatures and facilitate rapid queries through Locality Sensitive Hashing. These techniques reduce query times from hours using industrial desktop machines operating on the full graph to milliseconds on standard laptops. Our method allows exploration of strongly associated regions (i.e., communities) of large graphs in real-time on a laptop. It has been deployed in software that is actively used by social network analysts and offers another channel for media owners to monetize their data, helping them to continue to provide

  • CONFERENCE PAPER
    Kamthe S, Deisenroth MP, 2018,

    Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control.

    , Artificial Intelligence and Statistics, Publisher: PMLR, Pages: 1701-1710
  • JOURNAL ARTICLE
    Law M, Russo A, Broda K, 2018,

    The complexity and generality of learning answer set programs

    , ARTIFICIAL INTELLIGENCE, Vol: 259, Pages: 110-146, ISSN: 0004-3702
  • JOURNAL ARTICLE
    Muggleton S, Dai WZ, Sammut C, Tamaddoni-Nezhad A, Wen J, Zhou ZHet al., 2018,

    Meta-Interpretive Learning from noisy images

    , Machine Learning, Vol: 107, Pages: 1097-1118, ISSN: 0885-6125

    Statistical machine learning is widely used in image classification. However, most techniques (1) require many images to achieve high accuracy and (2) do not provide support for reasoning below the level of classification, and so are unable to support secondary reasoning, such as the existence and position of light sources and other objects outside the image. This paper describes an Inductive Logic Programming approach called Logical Vision which overcomes some of these limitations. LV uses Meta-Interpretive Learning (MIL) combined with low-level extraction of high-contrast points sampled from the image to learn recursive logic programs describing the image. In published work LV was demonstrated capable of high-accuracy prediction of classes such as regular polygon from small numbers of images where Support Vector Machines and Convolutional Neural Networks gave near random predictions in some cases. LV has so far only been applied to noise-free, artificially generated images. This paper extends LV by (a) addressing classification noise using a new noise-telerant version of the MIL system Metagol, (b) addressing attribute noise using primitive-level statistical estimators to identify sub-objects in real images, (c) using a wider class of background models representing classical 2D shapes such as circles and ellipses, (d) providing richer learnable background knowledge in the form of a simple but generic recursive theory of light reflection. In our experiments we consider noisy images in both natural science settings and in a RoboCup competition setting. The natural science settings involve identification of the position of the light source in telescopic and microscopic images, while the RoboCup setting involves identification of the position of the ball. Our results indicate that with real images the new noise-robust version of LV using a single example (i.e. one-shot LV) converges to an accuracy at least comparable to a thirty-shot statistical machine learner on bot

  • CONFERENCE PAPER
    Olofsson S, Deisenroth MP, Misener R, 2018,

    Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches.

    , Publisher: JMLR.org, Pages: 3905-3914
  • CONFERENCE PAPER
    Sæmundsson S, Hofmann K, Deisenroth MP, 2018,

    Meta reinforcement learning with latent variable Gaussian processes

    , Uncertainty in Artificial Intelligence (UAI) 2018, Publisher: Association for Uncertainty in Artificial Intelligence (AUAI)

    Learning from small data sets is critical inmany practical applications where data col-lection is time consuming or expensive, e.g.,robotics, animal experiments or drug design.Meta learning is one way to increase the dataefficiency of learning algorithms by general-izing learned concepts from a set of trainingtasks to unseen, but related, tasks. Often, thisrelationship between tasks is hard coded or re-lies in some other way on human expertise.In this paper, we frame meta learning as a hi-erarchical latent variable model and infer therelationship between tasks automatically fromdata. We apply our framework in a model-based reinforcement learning setting and showthat our meta-learning model effectively gen-eralizes to novel tasks by identifying how newtasks relate to prior ones from minimal data.This results in up to a60%reduction in theaverage interaction time needed to solve taskscompared to strong baselines.

  • CONFERENCE PAPER
    Tavakoli A, Pardo F, Kormushev P, 2018,

    Action Branching Architectures for Deep Reinforcement Learning

    Discrete-action algorithms have been central to numerous recent successes ofdeep reinforcement learning. However, applying these algorithms tohigh-dimensional action tasks requires tackling the combinatorial increase ofthe number of possible actions with the number of action dimensions. Thisproblem is further exacerbated for continuous-action tasks that require finecontrol of actions via discretization. In this paper, we propose a novel neuralarchitecture featuring a shared decision module followed by several networkbranches, one for each action dimension. This approach achieves a linearincrease of the number of network outputs with the number of degrees of freedomby allowing a level of independence for each individual action dimension. Toillustrate the approach, we present a novel agent, called Branching DuelingQ-Network (BDQ), as a branching variant of the Dueling Double Deep Q-Network(Dueling DDQN). We evaluate the performance of our agent on a set ofchallenging continuous control tasks. The empirical results show that theproposed agent scales gracefully to environments with increasing actiondimensionality and indicate the significance of the shared decision module incoordination of the distributed action branches. Furthermore, we show that theproposed agent performs competitively against a state-of-the-art continuouscontrol algorithm, Deep Deterministic Policy Gradient (DDPG).

  • JOURNAL ARTICLE
    Arulkumaran K, Deisenroth MP, Brundage M, Bharath AAet al., 2017,

    A brief survey of deep reinforcement learning

    , IEEE Signal Processing Magazine, Vol: 34, Pages: 26-38, ISSN: 1053-5888

    Deep reinforcement learning (DRL) is poised to revolutionize the field of artificial intelligence (AI) and represents a step toward building autonomous systems with a higherlevel understanding of the visual world. Currently, deep learning is enabling reinforcement learning (RL) to scale to problems that were previously intractable, such as learning to play video games directly from pixels. DRL algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of RL, then progress to the main streams of value-based and policy-based methods. Our survey will cover central algorithms in deep RL, including the deep Q-network (DQN), trust region policy optimization (TRPO), and asynchronous advantage actor critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via RL. To conclude, we describe several current areas of research within the field.

  • CONFERENCE PAPER
    Bao Z, Čyras K, Toni F, 2017,

    ABAplus: Attack Reversal in Abstract and Structured Argumentation with Preferences

    , Pages: 420-437, ISSN: 0302-9743

    © 2017, Springer International Publishing AG. We present ABAplus, a system that implements reasoning with the argumentation formalism ABA+. ABA+is a structured argumentation formalism that extends Assumption-Based Argumentation (ABA) with preferences and accounts for preferences via attack reversal. ABA+also admits as instance Preference-based Argumentation which accounts for preferences by reversing attacks in abstract argumentation (AA). ABAplus readily implements attack reversal in both AA and ABA-style structured argumentation. ABAplus affords computation, visualisation and comparison of extensions under five argumentation semantics. It is available both as a stand-alone system and as a web application.

  • CONFERENCE PAPER
    Baroni P, Comini G, Rago A, Toni Fet al., 2017,

    Abstract Games of Argumentation Strategy and Game-Theoretical Argument Strength

    , PRIMA, Publisher: Springer, Pages: 403-419, ISSN: 0302-9743

    We define a generic notion of abstract games of argumentation strategy for (attack-only and bipolar) argumentation frameworks, which are zero-sum games whereby two players put forward sets of arguments and get a reward for their combined choices. The value of these games, in the classical game-theoretic sense, can be used to define measures of (quantitative) game-theoretic strength of arguments, which are different depending on whether either or both players have an “agenda” (i.e. an argument they want to be accepted). We show that this general scheme captures as a special instance a previous proposal in the literature (single agenda, attack-only frameworks), and seamlessly supports the definition of a spectrum of novel measures of game-theoretic strength where both players have an agenda and/or bipolar frameworks are considered. We then discuss the applicability of these instances of game-theoretic strength in different contexts and analyse their basic properties.

  • JOURNAL ARTICLE
    Bellotti A, 2017,

    Reliable region predictions for automated valuation models

    , ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, Vol: 81, Pages: 71-84, ISSN: 1012-2443
  • CONFERENCE PAPER
    Chabierski P, Russo A, Law M, Broda Ket al., 2017,

    Machine comprehension of text using combinatory categorial grammar and answer set programs

    , ISSN: 1613-0073

    © 2017 CEUR-WS. All rights reserved. We present an automated method for generating Answer Set Programs from narratives written in English and demonstrate how such a representation can be used to answer questions about text. The proposed approach relies on a transparent interface between the syntax and semantics of natural language provided by Combinatory Categorial Grammars to translate text into Answer Set Programs, hence creating a knowledge base that, together with background knowledge, can be queried.

  • CONFERENCE PAPER
    Chamberlain BP, Cardoso A, Liu CHB, Pagliari R, Deisenroth MPet al., 2017,

    Customer Lifetime Value Prediction Using Embeddings

    , International Conference on Knowledge Discovery and Data Mining, Publisher: ACM, Pages: 1753-1762

    We describe the Customer LifeTime Value (CLTV) prediction system deployed atASOS.com, a global online fashion retailer. CLTV prediction is an importantproblem in e-commerce where an accurate estimate of future value allowsretailers to effectively allocate marketing spend, identify and nurture highvalue customers and mitigate exposure to losses. The system at ASOS providesdaily estimates of the future value of every customer and is one of thecornerstones of the personalised shopping experience. The state of the art inthis domain uses large numbers of handcrafted features and ensemble regressorsto forecast value, predict churn and evaluate customer loyalty. Recently,domains including language, vision and speech have shown dramatic advances byreplacing handcrafted features with features that are learned automaticallyfrom data. We detail the system deployed at ASOS and show that learning featurerepresentations is a promising extension to the state of the art in CLTVmodelling. We propose a novel way to generate embeddings of customers, whichaddresses the issue of the ever changing product catalogue and obtain asignificant improvement over an exhaustive set of handcrafted features.

  • CONFERENCE PAPER
    Chamberlain BP, Humby C, Deisenroth MP, 2017,

    Probabilistic Inference of Twitter Users' Age Based on What They Follow.

    , Publisher: Springer, Pages: 191-203
  • CONFERENCE PAPER
    Cocarascu O, Toni F, 2017,

    Identifying attack and support argumentative relations using deep learning.

    , Publisher: Association for Computational Linguistics, Pages: 1374-1379
  • JOURNAL ARTICLE
    Dawes TJW, de Marvao A, Shi W, Fletcher T, Watson GMJ, Wharton J, Rhodes CJ, Howard LSGE, Gibbs JSR, Rueckert D, Cook SA, Wilkins MR, O'Regan DPet al., 2017,

    Machine Learning of Three-dimensional Right Ventricular Motion Enables Outcome Prediction in Pulmonary Hypertension: A Cardiac MR Imaging Study

    , RADIOLOGY, Vol: 283, Pages: 381-390, ISSN: 0033-8419
  • CONFERENCE PAPER
    Dragiev S, Russo A, Broda K, Law M, Turliuc Ret al., 2017,

    An abductive-inductive algorithm for probabilistic inductive logic programming

    , Pages: 20-26, ISSN: 1613-0073

    The integration of abduction and induction has lead to a variety of non-monotonic ILP systems. XHAIL is one of these systems, in which abduction is used to compute hypotheses that subsume Kernel Sets. On the other hand, Peircebayes is a recently proposed logic-based probabilistic programming approach that combines abduction with parameter learning to learn distributions of most likely explanations. In this paper, we propose an approach for integrating probabilistic inference with ILP. The basic idea is to redefine the inductive task of XHAIL as a statistical abduction, and to use Peircebayes to learn probability distribution of hypotheses. An initial evaluation of the proposed algorithm is given using synthetic data.

  • JOURNAL ARTICLE
    Eleftheriadis S, Rudovic O, Deisenroth MP, Pantic Met al., 2017,

    Gaussian Process Domain Experts for Modeling of Facial Affect

    , IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol: 26, Pages: 4697-4711, ISSN: 1057-7149

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-t4-html.jsp Request URI: /respub/WEB-INF/jsp/search-t4-html.jsp Query String: id=989&limit=20&respub-action=search.html Current Millis: 1542824856255 Current Time: Wed Nov 21 18:27:36 GMT 2018