Intelligent Systems
The Intelligent Systems Group conducts research into the theory and application of artificial intelligence aimed at understanding and formalising aspects of intelligent behaviour for use in systems.
The group research themes are aimed at understanding and formalising aspects of intelligent behaviour for use in systems. Techniques, together with algorithms, and prototype software, are being developed for a variety of applications. These techniques are increasingly important in building more robust and more intelligent computing-based technologies.
Research topics in the group include computational statistics, machine learning, applications of machine learning to natural language processing, applications of machine learning to medical image processing, probabilistic reasoning, and computational models of argument.
The Intelligent Systems Group plays a key role in the UCL Centre for Computational Statistics and Machine Learning
Study
The Intelligent Systems Group is part of the UCL Department of Computer Science, and conducts research into the theory and application of artificial intelligence. Currently we have around 30 Phd students working on various aspects of the subject. We are keen to admit new PhD studies, and we welcome enquiries from prospective students.
Funding for PhD studies comes from a variety of sources including Doctoral Training Centres (e.g. VEIV, SeCRET, COMPLEX, Financial Computing etc), EPSRC studentships, UCL scholarships, industry sponsors (e.g. SAP, Intel, Google, Microsoft, etc), and research projects (e.g. EPSRC, EU, etc).
If you are interested in studying for a PhD in our group, you could look at the homepages for the academic members of the group to find a potential supervisor, or you could go to the department webpage on applying for PhD studies.
Recent publications
2018
Amgoud, L., Besnard, P., Hunter, A. (2018). Foundations for a logic of arguments. Journal of Applied Non-Classical Logics, 1-18. doi:10.1080/11663081.2018.1439356 |
Aste, T., Divos, P., Del Bano Rollin, S., Bihari, Z. (2018). Risk-Neutral Pricing and Hedging of In-Play Football Bets. Applied Mathematical Finance, doi:10.1080/1350486X.2018.1535275 |
Batrinca, B., Hesse, C.W., Treleaven, P.C. (2018). Examining drivers of trading volume in European markets. International Journal of Finance and Economics, 23 (2), 134-154. doi:10.1002/ijfe.1608 |
Batrinca, B., Hesse, C.W., Treleaven, P.C. (2018). European trading volumes on cross-market holidays. International Journal of Finance and Economics, 23 (4), 675-704. doi:10.1002/ijfe.1643 |
Baumann, T., Graepel, T., Shawe-Taylor, J. (2018). Adaptive Mechanism Design: Learning to Promote Cooperation.. CoRR, abs/1806.04067 |
Catling, F., Spithourakis, G.P., Riedel, S. (2018). Towards automated clinical coding. International Journal of Medical Informatics, 120 50-61. doi:10.1016/j.ijmedinf.2018.09.021 |
Cavallo, A., Romeo, L., Ansuini, C., Podda, J., Battaglia, F., Veneselli, E., ...Becchio, C. (2018). Prospective motor control obeys to idiosyncratic strategies in autism. SCIENTIFIC REPORTS, 8 doi:10.1038/s41598-018-31479-2 |
Chalaguine, L.A., Hamilton, F.L., Hunter, A., Potts, H.W.W. (2018). Argument harvesting using chatbots. Frontiers in Artificial Intelligence and Applications, 305 149-160. doi:10.3233/978-1-61499-906-5-149 |
Chalaguine, L.A., Hunter, A. (2018). Chatbot Design for Argument Harvesting. |
Christensen, A.P., Kenett, Y.N., Aste, T., Silvia, P.J., Kwapil, T.R. (2018). Network structure of the Wisconsin Schizotypy Scales–Short Forms: Examining psychometric network filtering approaches. Behavior Research Methods, 1-20. doi:10.3758/s13428-018-1032-9 |
Ciliberto, C., Herbster, M., Ialongo, A.D., Pontil, M., Rocchetto, A., Severini, S., Wossnig, L. (2018). Quantum machine learning: a classical perspective. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 474 (2209), doi:10.1098/rspa.2017.0551 |
Combettes, P.L., McDonald, A.M., Micchelli, C.A., Pontil, M. (2018). Learning with optimal interpolation norms. Numerical Algorithms, 1-23. doi:10.1007/s11075-018-0568-1 |
De Bona, G., Grant, J., Hunter, A., Konieczny, S. (2018). Towards a Unified Framework for Syntactic Inconsistency Measures. |
Engin, Z., Treleaven, P. (2018). Algorithmic Government: Automating Public Services and Supporting Civil Servants in using Data Science Technologies. The Computer Journal, doi:10.1093/comjnl/bxy082 |
Ferreira, F.S., Rosa, M.J., Moutoussis, M., Dolan, R., Shawe-Taylor, J., Ashburner, J., Miranda, J.M. (2018). Sparse PLS hyper-parameters optimisation for investigating brain-behaviour relationships.. |
Franceschi, L., Frasconi, P., Salzo, S., Grazzi, R., Pontil, M. (2018). Bilevel Programming for Hyperparameter Optimization and Meta-Learning.. |
Hadoux, E., Hunter, A., Polberg, S. (2018). Biparty Decision Theory for Dialogical Argumentation. |
Hirsch, R.D., Reynolds, M. (2018). The temporal logic of two dimensional Minkowski spacetime is decidable. Journal of Symbolic Logic, |
Hunter, A. (2018). Towards a framework for computational persuasion with applications in behaviour change. Argument and Computation, 9 (1), 15-40. doi:10.3233/AAC-170032 |
Hunter, A. (2018). Invited talk: Computational persuasion with applications in behaviour change. |
Hunter, A., Hadoux, E. (2018). Learning and Updating User Models for Subpopulations in Persuasive Argumentation Using Beta Distributions. |
Hunter, A., Hadoux, E., Corrégé, J.-.B. (2018). Strategic Dialogical Argumentation Using Multi-criteria Decision Making with Application to Epistemic and Emotional Aspects of Arguments. |
Hunter, A., Polberg, S. (2018). Empirical Methods for Modelling Persuadees in Dialogical Argumentation. |
Innes, M., Karpinski, S., Shah, V., Barber, D., Saito Stenetorp, P.L.E.P.S., Besard, T., ...Edelman, A. (2018). On Machine Learning and Programming Languages. |
Mitchell, J., Saito Stenetorp, P.L.E.P.S., Minervini, P., Riedel, S. (2018). Extrapolation in NLP. |
Nava, N., Di Matteo, T., Aste, T. (2018). Dynamic correlations at different time-scales with empirical mode decomposition. Physica A: Statistical Mechanics and its Applications, 502 534-544. doi:10.1016/j.physa.2018.02.108 |
Pappalardo, G., Di Matteo, T., Caldarelli, G., Aste, T. (2018). Blockchain inefficiency in the Bitcoin peers network. EPJ DATA SCIENCE, 7 doi:10.1140/epjds/s13688-018-0159-3 |
Phillips, R.C., Gorse, D. (2018). Cryptocurrency price drivers: Wavelet coherence analysis revisited. PLOS ONE, 13 (4), doi:10.1371/journal.pone.0195200 |
Phillips, R.C., Gorse, D. (2018). Predicting cryptocurrency price bubbles using social media data and epidemic modelling. |
Polberg, S., Hunter, A. (2018). Empirical evaluation of abstract argumentation: Supporting the need for bipolar and probabilistic approaches. International Journal of Approximate Reasoning, doi:10.1016/j.ijar.2017.11.009 |
Shah, H., Zheng, B., Barber, D. (2018). Generating Sentences Using a Dynamic Canvas. |
Shirley, M.K., Cole, T.J., Charoensiriwath, S., Treleaven, P., Wells, J.C.K. (2018). Differential investment in body girths by sex: Evidence from 3D photonic scanning in a Thai cohort (vol 163, pg 696, 2017). AMERICAN JOURNAL OF PHYSICAL ANTHROPOLOGY, 165 (2), 409. doi:10.1002/ajpa.23359 |
Thimm, M., Polberg, S., Hunter, A. (2018). Epistemic attack semantics. |
Uurtio, V., Monteiro, J.M., Kandola, J., Shawe-Taylor, J., Fernandez-Reyes, D., Rousu, J. (2018). A tutorial on canonical correlation methods. ACM Computing Surveys (CSUR), 50 (6), 1-33. doi:10.1145/3136624 |
Weissenborn, D., Minervini, P., Augenstein, I., Welbl, J., Rocktaschel, T., Bosnjak, M., ...Riedel, S. (2018). Jack the Reader - A Machine Reading Framework. |
Welbl, J., Saito Stenetorp, P.L.E.P.S., Riedel, S. (2018). Constructing Datasets for Multi-hop Reading Comprehension Across Documents. Transactions of the Association for Computational Linguistics, |
Wu, X., Kim, G.H., Salisbury, M.L., Barber, D., Bartholmai, B.J., Brown, K.K., ...Gruden, J.F. (2018). Computed Tomographic Biomarkers in Idiopathic Pulmonary Fibrosis: The Future of Quantitative Analysis.. American journal of respiratory and critical care medicine, doi:10.1164/rccm.201803-0444pp |
2017
Alquier, P., Mai, T.T., Pontil, M. (2017). Regret Bounds for Lifelong Learning.. |
Anthony, T., Tian, Z., Barber, D. (2017). Thinking Fast and Slow with Deep Learning and Tree Search. |
Aste, T., Di Matteo, T. (2017). Sparse Causality Network Retrieval from Short Time Series. COMPLEXITY, doi:10.1155/2017/4518429 |
Aste, T., Tasca, P., Di Matteo, T. (2017). Blockchain Technologies: The Foreseeable Impact on Society and Industry. COMPUTER, 50 (9), 18-28. doi:10.1109/MC.2017.3571064 |
Atkinson, K., Baroni, P., Giacomin, M., Hunter, A., Prakken, H., Reed, C., ...Villata, S. (2017). Toward Artificial Argumentation. AI MAGAZINE, 38 (3), 25-36. doi:10.1609/aimag.v38i3.2704 |
Badino, L., Franceschi, L., Arora, R., Donini, M., Pontil, M. (2017). A speaker adaptive DNN training approach for speaker-independent acoustic inversion. |
Baldassarre, L., Pontil, M., Mourão-Miranda, J. (2017). Sparsity Is Better with Stability: Combining Accuracy and Stability for Model Selection in Brain Decoding.. Front Neurosci, 11 62. doi:10.3389/fnins.2017.00062 |
Bohné, J., Ying, Y., Gentric, S., Pontil, M. (2017). Learning local metrics from pairwise similarity data. Pattern Recognition, doi:10.1016/j.patcog.2017.04.002 |
Bošnjak, M., Rocktäschel, T., Naradowsky, J., Riedel, S. (2017). Programming with a differentiable forth interpreter. |
Botev, A., Lever, G., Barber, D. (2017). Nesterov's accelerated gradient and momentum as approximations to regularised update descent. |
Botev, A., Ritter, J., Barber, D. (2017). Practical Gauss-Newton Optimisation for Deep Learning. |
Buonocore, R.J., Aste, T., Di Matteo, T. (2017). Asymptotic scaling properties and estimation of the generalized Hurst exponents in financial data. PHYSICAL REVIEW E, 95 (4), doi:10.1103/PhysRevE.95.042311 |
Chen, H., Cheng, T., Shawe-Taylor, J. (2017). A Balanced Route Design for Min-Max Multiple-Depot Rural Postman Problem (MMMDRPP): a police patrolling case. International Journal of Geographical Information Science, 1-22. doi:10.1080/13658816.2017.1380201 |
Ciliberto, C., Rudi, A., Rosasco, L., Pontil, M. (2017). Consistent Multitask Learning with Nonlinear Output Relations.. |
Ciliberto, C., Rudi, A., Rosasco, L., Pontil, M. (2017). Consistent Multitask Learning with Nonlinear Output Relations.. |
Cinelli, M., Sun, Y., Best, K., Heather, J.M., Reich-Zeliger, S., Shifrut, E., ...Chain, B. (2017). Feature selection using a one dimensional naïve Bayes' classifier increases the accuracy of support vector machine classification of CDR3 repertoires.. Bioinformatics, doi:10.1093/bioinformatics/btw771 |
Coniglio, A., Pica Ciamarra, M., Aste, T. (2017). Universal behaviour of the glass and the jamming transitions in finite dimensions for hard spheres.. Soft Matter, doi:10.1039/c7sm01481c |
Cousins, S., Shawe-Taylor, J. (2017). High-probability minimax probability machines. Machine Learning, 1-24. doi:10.1007/s10994-016-5616-2 |
De Bona, G., Hunter, A. (2017). Localising iceberg inconsistencies. Artificial Intelligence, 246 118-151. doi:10.1016/j.artint.2017.02.005 |
Franceschi, L., Donini, M., Frasconi, P., Pontil, M. (2017). Forward and Reverse Gradient-Based Hyperparameter Optimization. |
Franceschi, L., Donini, M., Frasconi, P., Pontil, M. (2017). Forward and reverse gradient-based hyperparameter optimization. |
Grant, J., Hunter, A. (2017). Analysing inconsistent information using distance-based measures. International Journal of Approximate Reasoning, 89 3-26. doi:10.1016/j.ijar.2016.04.004 |
Hadoux, E., Hunter, A. (2017). Strategic Sequences of Arguments for Persuasion Using Decision Trees. |
Hadoux, E., Hunter, A. (2017). Computationally Viable Handling of Beliefs in Arguments for Persuasion. |
Han, G., Menezes, M., Halaseh, L., Stuczyński, J., Menara, D., Riedel, S., Saito Stenetorp, P.L.E.P.S. (2017). Towards a Word Sheriff 2.0: Lessons learnt and the road ahead. |
He, Z., Gao, S., Xiao, L., Barber, D. (2017). Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning. |
Hirsch, R.D., McLean, B. (2017). Disjoint union partial algebras. Logical Methods in Computer Science, doi:10.23638/LMCS-13(2:10)2017 |
Hunter, A., Potyka, N. (2017). Updating probabilistic epistemic states in persuasion dialogues. |
Hunter, A., Thimm, M. (2017). Probabilistic Reasoning with Abstract Argumentation Frameworks. JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 59 565-611. doi:10.1613/jair.5393 |
Ivan Sanchez Carmona, V., Riedel, S. (2017). How well can we predict hypernyms fromword embeddings? A dataset-centric analysis. |
Johnston, M., Michie, S., West, R., Thomas, J., Mac Aonghusa, P., Shawe-Taylor, J., Kelly, M. (2017). THE HUMAN BEHAVIOUR CHANGE PROJECT: DEVELOPMENT OF AN AUTOMATED SYSTEM TO SYNTHESISE EVALUATIONS OF BEHAVIOUR CHANGE INTERVENTIONS TO FURTHER THE SCIENCE AND APPLICATION OF BEHAVIOUR CHANGE. |
Kempinska, K., Longley, P., Shawe-Taylor, J. (2017). Interactional regions in cities: making sense of flows across networked systems.International Journal of Geographical Information Science, 1-20. doi:10.1080/13658816.2017.1418878 |
Kolchyna, O., Treleaven, P.C., Souza, T.T.P., Aste, T. (2017). A Framework for Twitter Events Detection, Differentiation and its Application for Retail Brands. |
Law, T., Shawe-Taylor, J. (2017). Practical Bayesian support vector regression for financial time series prediction and market condition change detection. Quantitative Finance, 1-14. doi:10.1080/14697688.2016.1267868 |
Liepins, R., Germann, U., Barzdins, G., Birch, A., Renals, S., Weber, S., ...Klejch, O. (2017). The SUMMA platform prototype. |
Livan, G., Caccioli, F., Aste, T. (2017). Excess reciprocity distorts reputation in online social networks.. Sci Rep, 7 (1), 3551. doi:10.1038/s41598-017-03481-7 |
Malki, K., Tosto, M.G., Mourino-Talın, H., Rodrıguez-Lorenzo, S., Pain, O., Jumhaboy, I., ...Malykh, A. (2017). Highly Polygenic Architecture of Antidepressant Treatment Response: Comparative Analysis of SSRI and NRI Treatment in an Animal Modelof Depression. American Journal of Medical Genetics Part B: Neuropsychiatric Genetics, doi:10.1002/ajmg.b.32494 |
Mann, A.D., Gorse, D. (2017). Deep Candlestick Mining. |
Mann, A.D., Gorse, D. (2017). A new methodology to exploit predictive power in (open, high, low, close) data. |
Massara, G.P., Matteo, T.D., Aste, T. (2017). Network Filtering for Big Data: Triangulated Maximally Filtered Graph.. J. Complex Networks, 5 161-178. doi:10.1093/comnet/cnw015 |
Michie, S., Thomas, J., Johnston, M., Aonghusa, P.M., Shawe-Taylor, J., Kelly, M.P., ...Norris, E. (2017). The Human Behaviour-Change Project: harnessing the power of artificial intelligence and machine learning for evidence synthesis and interpretation. Implementation Science, 12 (1), 121. doi:10.1186/s13012-017-0641-5 |
Minervini, P., Demeester, T., Rocktäschel, T., Riedel, S. (2017). Adversarial sets for regularising neural link predictors. |
Musmeci, N., Nicosia, V., Aste, T., Di Matteo, T., Latora, V. (2017). The Multiplex Dependency Structure of Financial Markets.COMPLEXITY, doi:10.1155/2017/9586064 |
Noor, K., Hunter, A., Mayer, A. (2017). Analysis of medical arguments from patient experiences expressed on the social web. |
O'Brien, J., Hunter, A. (2017). Reasoning with spatial logics A prototype iconographic tool for deliberation in urban domains. |
Pavisic, I.M., Firth, N.F., Parsons, S., Martinez Rego, D., Shakespeare, T.J., Yong, K.X.X., ...Macpherson, K. (2017). Eyetracking Metrics in Young Onset Alzheimer’s Disease: A Window into Cognitive Visual Functions. Frontiers in Neurology, |
Peng, P., Tian, Y., Xiang, T., Wang, Y., Pontil, M., Huang, T. (2017). Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, doi:10.1109/TPAMI.2017.2723882 |
Phillips, R.C., Gorse, D. (2017). Predicting Cryptocurrency Price Bubbles Using Social Media Data and Epidemic Modelling. |
Polberg, S., Hunter, A., Thimm, M. (2017). Belief in attacks in epistemic probabilistic argumentation. |
Rocktäschel, T., Riedel, S. (2017). End-to-end Differentiable Proving. |
Shah, H., Barber, D., Botev, A. (2017). Overdispersed variational autoencoders. |
Shimaoka, S., Stenetorp, P., Inui, K., Riedel, S. (2017). Neural architectures for fine-grained entity type classification. |
Shirley, M.K., Cole, T.J., Charoensiriwath, S., Treleaven, P., Wells, J.C.K. (2017). Differential investment in body girths by sex: evidence from 3D photonic scanning in a Thai cohort. American Journal of Physical Anthropology, doi:10.1002/ajpa.23238 |
Singh, G., Marshall, I.J., Thomas, J., Shawe-Taylor, J., Wallace, B.C. (2017). A neural candidate-selector architecture for automatic structured clinical text annotation. |
Sun, Y., Best, K., Cinelli, M., Heather, J.M., Reich-Zeliger, S., Shifrut, E., ...Chain, B. (2017). Specificity, Privacy, and Degeneracy in the CD4 T Cell Receptor Repertoire Following Immunization.. Frontiers in Immunology, 8 430. doi:10.3389/fimmu.2017.00430 |
Treleaven, P., Brown, R.G., Yang, D. (2017). Blockchain Technology in Finance. COMPUTER, 50 (9), 14-17. doi:10.1109/MC.2017.3571047 |
Trouillon, T., Dance, C.R., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G. (2017). Knowledge Graph Completion via Complex Tensor Factorization. Journal of Machine Learning Research, 18 (130), 1-38. |